uw-analyze-infrastructure
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted files from the codebase (e.g., build manifests, Dockerfiles, and configuration files) to generate documentation.\n
- Ingestion points: The skill is instructed to search for and read various infrastructure files using the
Read,Grep, andGlobtools.\n - Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions that might be embedded within the analyzed infrastructure files, such as malicious comments in a Dockerfile or package manifest.\n
- Capability inventory: The agent has permission to write and edit files in the
docs/unwind/directory and execute restricted shell commands (mkdir,ls).\n - Sanitization: There is no specified sanitization process for the data extracted from the codebase before it is formatted and written into the documentation output.
Audit Metadata