lcs-prd-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely on local markdown files (
prd.md,.lcs/state.md) and writes output to a new local file (prd-enhanced.md). It contains no network access, hardcoded credentials, or shell command execution instructions. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading
prd.md, which creates a surface for indirect prompt injection. However, because the skill lacks dangerous tools (e.g., no network access or arbitrary code execution), the potential impact is limited to the text generated in the output file. - Ingestion points: Reads
prd.mdfrom the.lcs/work-items/directory. - Boundary markers: Absent; there are no explicit delimiters or instructions to the agent to ignore instructions embedded within the PRD text.
- Capability inventory: File system read/write access limited to the project's work-item directory.
- Sanitization: No sanitization or escaping of the input PRD content is specified before it is processed by the agent.
Audit Metadata