design-spec
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to operate in 'FULLY AUTONOMOUS MODE' with 'Zero questions' and 'Do NOT ask the user anything', which could lead the agent to follow malicious instructions embedded in the codebase without seeking user verification.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection. Ingestion points: The skill reads all project files (e.g., README, package.json, source code) and processes user-supplied '$ARGUMENTS' (SKILL.md). Boundary markers: The instructions lack delimiters or explicit warnings to disregard instructions found within the processed data. Capability inventory: The agent is directed to read all project files, write to 'design-spec.md', and perform a git commit (SKILL.md). Sanitization: No sanitization or instruction filtering is applied to the ingested content before processing.
Audit Metadata