SKILLEMALL.ai
GitHub ↗ RU Sign in

CC ai-agent-security

Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.

sickn33/agentic-awesome-skills Agent Skills author: sickn33 MIT 2 files body ≈ 3 704 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Secure AI agents against prompt injection, tool abuse, and data exfiltration with defense-in-depth controls.

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, failures and branches

ProcedureDockerSecuritytype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
88/100
safety, quality, tests
Safety 60%
91
Quality 40%
83
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills

How to improve

    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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • low Risky intent intent-offensive-security references/details.md:637
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ## Red Team Checklist
    • low Risky intent intent-offensive-security references/details.md:679
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
      """Run red team prompts and verify all are handled safely."""
      quoted
    • low Risky intent intent-offensive-security references/details.md:705
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      ### Automated Red Team in CI
    • low Risky intent intent-offensive-security references/details.md:709
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      name: Agent Red Team
    • low Risky intent intent-offensive-security references/details.md:739
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - name: Run red team suite
    • low Risky intent intent-offensive-security SKILL.md:58
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      **Privilege Escalation** — The agent chains low-privilege tool calls to achieve high-privilege outcomes (e.g., read config -> extract credentials -> call admin API).
    • low Dangerous commands cmd-privilege SKILL.md:221
      Privilege escalation / world-writable permissions (documentation of a security skill)
      sudo tee /etc/apt/sources.list.d/gvisor.list
      security skill
    • low Risky intent intent-offensive-security SKILL.md:365
      Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
      - [Red Team Checklist](references/details.md)

    A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

    Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "risk"
    • note frontmatter-key unknown frontmatter key "source"
    • note frontmatter-key unknown frontmatter key "source_repo"
    • note frontmatter-key unknown frontmatter key "source_type"
    • note frontmatter-key unknown frontmatter key "date_added"
    • note frontmatter-key unknown frontmatter key "license_source"

    Process rating: all ten parameters 51/100

    • 0Result and completion. Does not say what the result is
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 2 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 24 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3704 tokens

    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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Description length 108: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 24 items
    • +4Has examples (6 code blocks)
    • +4Reference files are cited in the instructions (1 of 1)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.