readme-craftsman

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data from the repository to perform its tasks.
  • Ingestion points: The skill reads numerous untrusted files from the repository during the analysis phase, including package.json, pyproject.toml, requirements.txt, and other configuration or source files (SKILL.md, Step 2).
  • Boundary markers: The instructions do not define clear delimiters or "ignore instructions" directives to prevent the agent from obeying instructions that may be embedded within the processed external files.
  • Capability inventory: The agent is granted filesystemWrite and shell capabilities (skill.json), which could be misused if the agent inadvertently follows instructions found in analyzed project files.
  • Sanitization: There is no explicit requirement for sanitizing or validating the content extracted from project files before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 02:13 PM