skills/ianphil/my-skills/implement/Gen Agent Trust Hub

implement

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several system commands as part of the TDD workflow, including cargo test, make lint, make check, and make build. It also runs a local Python script specs/tests/run_tests_claude.py to verify implementation against specifications.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it orchestrates agent behavior based on the contents of markdown files within the repository.\n
  • Ingestion points: Task instructions are read from tasks.md, and feature requirements are read from specs/tests/{feature-id}.md.\n
  • Boundary markers: The skill lacks explicit boundary markers or instructions to ignore malicious directives that might be embedded in the task or specification files.\n
  • Capability inventory: The skill allows the agent to execute shell commands, perform git operations, and modify project files.\n
  • Sanitization: Content from the ingested markdown files is not sanitized or validated before influencing the agent's decision-making process or command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:29 AM