context7-docs-fetcher

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external documentation service.
  • Ingestion points: Untrusted documentation content enters the agent context through the get-library-docs tool defined in references/agents/context7-docs-fetcher.md.
  • Boundary markers: Absent. There are no instructions to use delimiters or specific warnings to ignore embedded instructions within the fetched documentation.
  • Capability inventory: The agent has access to the mcp__ide__executeCode tool, which allows it to run code locally.
  • Sanitization: Absent. There is no evidence of filtering or validation of the fetched documentation before it is processed by the LLM.
  • [COMMAND_EXECUTION]: The skill configuration in references/agents/context7-docs-fetcher.md explicitly enables the mcp__ide__executeCode tool, granting the agent the capability to execute arbitrary code in the user's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:37 AM