documentation-lookup
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection by fetching and processing content from external documentation sources.
- Ingestion points: Data enters the agent's context through the output of the
query-docsMCP tool (SKILL.md). - Boundary markers: The skill does not instruct the agent to use delimiters or to ignore embedded instructions found within the documentation content (SKILL.md).
- Capability inventory: The skill is designed for use in environments like Claude Code or Cursor, which typically possess powerful capabilities such as file system access and shell command execution.
- Sanitization: While the skill correctly mandates the redaction of secrets from outgoing queries, it does not specify any sanitization or validation for the documentation content retrieved from the external service.
Audit Metadata