SKILLEMALL.ai
GitHub ↗ RU Sign in

FC context-compactor-cli

Condense a long agent session transcript into a compact handoff memo: decisions, tasks, risks, facts & links. Credential values are auto-redacted before output (best-effort - review memos before sharing; --strict drops whole suspect lines). EN/RU heuristics, zero dependencies. The CLI prints what it reads and where it writes. Use ONLY with the user's explicit consent: tell the user which transcript file will be read.

Blockedguard blocked the skill: signs of malicious behaviour
ClawHub Agent Skills author: ViBo v1.1.7 MIT-0 5 files body ≈ 664 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Condense a long agent session transcript into a compact handoff memo: decisions, tasks, risks, facts & links.

As a process C 56/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

IntegrationInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
35/100
safety, quality, tests
Safety 60%
0
Quality 40%
88
Run on models
none yet
Process rating
C
56/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten
Guard blocked this skill: critical findings below. Do not install it until the author fixes them.
This is a copy of a skill from another catalog; the rating counts the canonical one: context-compactor-cli (ClawHub)

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Secrets in code
If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

How to improve

  1. Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 15

  • critical Secrets in code secret-github-token compactor.py:299
    GitHub token (quoted — discussed, not commanded)
    "Ассистент: решили: gho_…789 для деплоя в CI.\n"
    quoted
  • critical Secrets in code secret-github-token compactor.py:301
    GitHub token (quoted — discussed, not commanded)
    "Ассистент: решили: ghs_…XYZ для раннера.\n"
    quoted
  • critical Secrets in code secret-aws-key compactor.py:349
    AWS access key ID (quoted — discussed, not commanded)
    "AKIA": "AKIAABCDEFGHIJKLMNOP",
    quoted
  • high Secrets in code secret-github-token compactor.py:335
    GitHub token (detector / deny-list definition)
    strict_gho = build_memo("decided: gho_…789 in vault\n",
    detector
Medium and low: 11
  • medium Secrets in code secret-private-key compactor.py:304
    Private key material (key header without key body; quoted — discussed, not commanded)
    "-----BEGIN PRIVATE KEY----- …
    header onlyquoted
  • medium Secrets in code secret-private-key compactor.py:361
    Private key material (key header without key body; quoted — discussed, not commanded)
    big_pem = "-----BEGIN PRIVATE KEY----- …\n"
    header onlyquoted
  • low Secrets in code secret-high-entropy-token compactor.py:299
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Ассистент: решили: gho_…789 для деплоя в CI.\n"
    quoted
  • low Secrets in code secret-github-token compactor.py:300
    GitHub token (placeholder value)
    "Ассистент: решили: ghu_…789 для вебхуков.\n"
    placeholder
  • low Secrets in code secret-high-entropy-token compactor.py:301
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Ассистент: решили: ghs_…XYZ для раннера.\n"
    quoted
  • low Secrets in code secret-high-entropy-token compactor.py:305
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "MIIE…ial\n"
    quoted
  • low Secrets in code secret-high-entropy-token compactor.py:307
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Ассистент: решили: BEGIN RSA PRIVATE KEY-…END RSA PRIVATE KEY----- для доступа по ssh.\n"
    quoted
  • low Secrets in code secret-high-entropy-token compactor.py:324
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    ok_jwt = "eyJh…CJ9" not in memo
    quoted
  • low Secrets in code secret-github-token compactor.py:341
    GitHub token (placeholder value)
    "ghp_": "ghp_ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijkl",
    placeholder
  • low Secrets in code secret-anthropic-key compactor.py:347
    Anthropic API key (placeholder value)
    "sk-ant-": "sk-ant-ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghi",
    placeholder
  • low Secrets in code secret-google-key compactor.py:350
    Google API key (placeholder value)
    "AIza": "AIzaABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijkl",
    placeholder

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • note frontmatter-key unknown frontmatter key "tools"

Process rating: all ten parameters 56/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 4 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 10 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 664 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • high The skill tells the model to perform an irreversible action with no human approval

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 420: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 10 items
  • +4Has examples (1 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

External checks

ClawHub: clean
This skill is a local transcript-compaction CLI with clear consent, privacy, and output warnings; the main caveat is an optional npx install path that adds an external package trust boundary.
LLM: benign (high) · VirusTotal: · 7 Sept 2026