Skills
skills/sirn/dotfiles/code-generate-tests/Gen Agent Trust Hub

code-generate-tests

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local commands jj diff and grep to identify code context and search for functions without tests in SKILL.md and SUBAGENT.md.\n- [REMOTE_CODE_EXECUTION]: It generates new test code and executes it using the test skill to verify coverage and correctness, which is the primary intended behavior defined in SKILL.md.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted project code. (Evidence: Ingestion points: jj diff and grep in SKILL.md; Boundary markers: Absent; Capability inventory: test skill invocation; Sanitization: Absent).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 04:55 PM