ork-implement

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from external third-party API documentation via the context7 MCP server. This architectural choice creates a surface for indirect prompt injection attacks, where malicious instructions embedded in external documentation could potentially influence or override the agent's behavior during the implementation phase.
  • Ingestion points: External data is fetched using the resolve-library-id and query-docs tools provided by the context7 MCP server (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or instructions to treat documentation content as untrusted data rather than system directives.
  • Capability inventory: The skill has the authority to perform code implementation, file modifications, and run verification tests, which provides a high-impact surface for any injected instructions to exploit (SKILL.md).
  • Sanitization: There are no documented procedures for sanitizing, escaping, or validating the content retrieved from external API documentation servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 04:00 AM
Security Audit — agent-trust-hub — ork-implement