academic-repo-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by design, as it ingests and processes data from external, untrusted repositories.\n
- Ingestion points: The skill reads file contents from the target repository, including the README, entry scripts (train, main, eval, inference), and model configuration files (Step 1 and Step 3).\n
- Boundary markers: The skill does not instruct the agent to use specific delimiters or protective boundary markers when processing these external files, increasing the risk of the agent accidentally following instructions embedded in the project data.\n
- Capability inventory: The skill uses the
bashtool to explore the file system and read repository content.\n - Sanitization: There is no evidence of sanitization, validation, or filtering of the content extracted from the files before it is used for documentation generation.
Audit Metadata