devdocs-system-design
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external data.
- Ingestion points: The skill reads
docs/devdocs/01-requirements.mdand project source code via file discovery tools. - Boundary markers: There are no explicit instructions or delimiters used to isolate processed requirement content from the agent's core instructions.
- Capability inventory: The agent possesses
Writecapabilities, allowing it to modify documentation based on ingested data. - Sanitization: No input validation or filtering is specified for the content of requirement files.
- Mitigation: The risk is addressed by the mandatory 'Plan Mode' requiring human approval before the agent executes design changes.
- [NO_CODE]: The skill package does not contain any executable scripts or binaries. It is composed entirely of Markdown instructions and templates.
Audit Metadata