press-release-faq
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to read existing files from the project environment (e.g., from directories like product/, strategy/, or prfaq/) to facilitate document updates. This functionality introduces a potential surface for indirect prompt injection if the files being ingested contain malicious instructions. However, the risk is minimal as the skill's capabilities are restricted to markdown file operations and do not include network or shell access.
- Ingestion points: The UPDATE and FIND modes read content from project-relative paths or user-specified locations.
- Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from following instructions embedded within the source files.
- Capability inventory: The skill is limited to reading and writing markdown documents; it lacks the capability to execute code or communicate with external servers.
- Sanitization: The skill does not validate or sanitize the content of the files it reads before processing.
Audit Metadata