review-prd
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it reads content from external files and interpolates it directly into instructions for subagents. A malicious payload within a PRD file could potentially influence the subagents or the primary agent's behavior during the consolidation and application of changes.
- Ingestion points: The skill reads
plans/<plan-name>/README.mdandAGENTS.mdfrom the local repository. - Boundary markers: The prompts used to spawn subagents interpolate file content without using secure delimiters or instructions to ignore potential commands embedded in the data.
- Capability inventory: The skill can read and write files (
plans/<plan-name>/README.md) and initiate new subagent tasks. - Sanitization: There is no evidence of sanitization, escaping, or validation of the content read from the files before it is processed by the LLM.
Audit Metadata