requirement-doc-review
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data which could contain malicious instructions targeted at the agent.
- Ingestion points: Processes external requirement documents, pasted text, and files from the workspace (
SKILL.md). - Boundary markers: The prompt instructions do not specify the use of clear delimiters to separate untrusted content from instructions, nor do they explicitly command the agent to ignore instructions found within the source material.
- Capability inventory: The skill utilizes file read and write operations to create multiple Markdown files in the local workspace (
SKILL.md,references/output-contract.md). - Sanitization: No sanitization or validation logic is defined to inspect or neutralize potential injection strings within the processed documents.
Audit Metadata