grounding-with-context7
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill encourages the agent to ingest and follow instructions from external, untrusted sources (documentation). This presents an indirect prompt injection risk.
- Ingestion points: Untrusted documentation content is brought into the agent context via the
query-docstool as specified in SKILL.md. - Boundary markers: The skill lacks instructions to wrap fetched documentation in boundary markers or to ignore instructions contained within that data.
- Capability inventory: The agent is expected to use the fetched data to write code, change configuration, and perform audits, which typically involve file system access and execution capabilities.
- Sanitization: There are no provisions for sanitizing or validating the content retrieved from external documentation before the agent acts upon it.
Audit Metadata