scope-check
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection by processing data from untrusted sources within the repository.\n
- Ingestion points: The skill reads content from design documents in
design/, sprint plans inproduction/, source code files for TODOs/FIXMEs, and git commit logs via theBashtool.\n - Boundary markers: No explicit delimiters or instructions are provided to the model to differentiate between its own instructions and the untrusted data read from files.\n
- Capability inventory: Access is limited to
Read,Glob,Grep, andBash(git log *). The skill lacks capabilities for network communication, file modification, or arbitrary command execution.\n - Sanitization: The instructions do not specify any sanitization or validation of the data retrieved from the files before it is processed by the model.
Audit Metadata