lighthouse-audit

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash(curl:*) tool to execute network requests against the Foghorn API. This is the primary mechanism for all functionality including authentication, site setup, and issue retrieval.- [EXTERNAL_DOWNLOADS]: The skill makes external calls to https://foghorn-api.artgaard.workers.dev. These requests are directed to the vendor's own infrastructure and are used to fetch configuration and audit results.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it retrieves and processes untrusted data from an external API.
  • Ingestion points: Data returned from GET /pages and GET /issues endpoints in SKILL.md, including page URLs, paths, and audit issue titles.
  • Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands in the API response data.
  • Capability inventory: The skill possesses the Bash(curl:*) capability across its operational scope, which allows it to make further network requests.
  • Sanitization: There is no evidence of sanitization, validation, or filtering of the text content received from the API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 04:28 AM