GitHub Project Analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions establish an attack surface for indirect prompt injection by directing the agent to process content from external, untrusted GitHub repositories. \n
- Ingestion points: The analysis process in
SKILL.md(Phase A) involves reading data from dependency files, architectural entry points, README files, and core source code files. \n - Boundary markers: The skill does not define specific delimiters or "ignore" instructions to separate untrusted repository content from the agent's primary task instructions. \n
- Capability inventory: The ingested data is used to generate resume bullets, assign engineering confidence scores, and perform qualitative grading of the repository. \n
- Sanitization: The skill lacks requirements for filtering, escaping, or validating the external text before it is interpolated into the agent's context for analysis.
Audit Metadata