BC tene-cli
Local-first encrypted secret management with the tene CLI. Activate when the user mentions secrets, API keys, credentials, tokens, .env files, environment variables, or asks to run a command that needs secrets injected. Enforces strict AI safety rules (never print plaintext, never read .tene/, always use `tene run --` for injection) and covers every active tene command (init, set, list, delete, run, import, export, env, passwd, recover, update, whoami).
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
How to improve
- 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
-
medium Risky intent
intent-wallet-secretsSKILL.md:114Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetAfter `init` the user will see a **12-word recovery phrase**. Remind them to
-
low Risky intent
intent-wallet-secretsexamples/01-init-and-first-secret.md:18Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)5. Remind the user to save the 12-word recovery phrase offline.
fixture -
low Dangerous commands
cmd-pipe-to-shellexamples/01-init-and-first-secret.md:26Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file; documentation of a security skill; the skill's own vendor host)curl -sSfL https://tene.sh/install.sh | sh
fixturesecurity skillvendor-host -
low Risky intent
intent-wallet-secretsexamples/01-init-and-first-secret.md:32Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file)# → prints: 12-word BIP-39 recovery phrase
fixture -
low Risky intent
intent-wallet-secretsexamples/01-init-and-first-secret.md:47Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (test fixture / example file; quoted — discussed, not commanded)> "Save the 12-word recovery phrase somewhere safe (password manager or
fixturequoted -
low Dangerous commands
cmd-pipe-to-shellexamples/03-multi-env-ci-cd.md:88Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file; documentation of a security skill; the skill's own vendor host)run: curl -sSfL https://tene.sh/install.sh | sh
fixturesecurity skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellREADME.md:29Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -sSfL https://tene.sh/install.sh | sh
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:78Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)curl -sSfL https://tene.sh/install.sh | sh
security skillvendor-host -
low Dangerous commands
cmd-pipe-to-shellSKILL.md:334Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)- run: curl -sSfL https://tene.sh/install.sh | sh
security skillvendor-host
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 12 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 32 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3196 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (4 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- -214 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 457: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.