system-design
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The file
references/output.mdcontains a shell command (grep -qxF '.artifacts' .git/info/exclude 2/dev/null || echo '.artifacts' >> .git/info/exclude) intended to ensure that the skill's output directory is excluded from Git tracking. This is a benign administrative task for repository maintenance. - [PROMPT_INJECTION]: The skill ingests untrusted user input during the discovery and requirements phases. While this creates an indirect prompt injection surface, the skill's capabilities are restricted to writing text files to a dedicated artifacts directory and providing structured guidance, which limits the potential impact.
- Ingestion points: User descriptions in
references/discovery.mdandreferences/requirements.md. - Boundary markers: None explicitly defined in instructions.
- Capability inventory: File system writes in
references/output.mdand handoffs to other agent skills inSKILL.md. - Sanitization: None specified for input data.
- [SAFE]: All referenced skills and installation sources belong to the same vendor context ('adeonir'), and no obfuscation or suspicious network activities were identified.
Audit Metadata