doc-brd-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation specifies the use of local bash commands to facilitate document review. Specifically, it uses sha256sum to compute file hashes for drift detection and grep to identify legacy naming patterns within the document text.
- [EXTERNAL_DOWNLOADS]: The skill includes functionality to verify the reachability of external documentation links, which involves performing network operations to check remote resource availability.
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection as it is designed to ingest and analyze untrusted content from Business Requirements Documents (BRDs).
- Ingestion points: The skill reads markdown files and section files located in the docs/01_BRD/ directory.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or isolate instructions that may be embedded within the documents being reviewed.
- Capability inventory: The agent has the capability to execute shell commands (grep, sha256sum, cut) and perform file system write operations to generate reports and update the .drift_cache.json file.
- Sanitization: There is no evidence of content sanitization or validation routines described to filter malicious input from the reviewed documents before processing.
Audit Metadata