verify-quality
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingest and analyzes local source files (e.g., *.py, *.ts, *.js) which are considered untrusted data and could contain malicious instructions intended to manipulate the agent's reporting or behavior.
- Ingestion points: The skill discovers and reads implementation files in directories such as
src/,lib/, andapp/during Step 1. - Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the source code files being reviewed.
- Capability inventory: While the skill body focuses on heuristics and reporting, the underlying agent may have broader capabilities (e.g., file system access) that could be targeted by an injection.
- Sanitization: There is no mention of sanitizing or escaping the content of the files before they are processed by the LLM for quality analysis.
Audit Metadata