remotion-docs

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process external content from documentation URLs, which creates a theoretical surface for indirect prompt injection if the source content is untrusted or compromised.
  • Ingestion points: Documentation pages retrieved from www.remotion.dev/docs/*.md based on search results from the Algolia API.
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat the fetched documentation content as untrusted data.
  • Capability inventory: The agent performs network requests to fetch documentation content and incorporates it into its reasoning context.
  • Sanitization: No sanitization or validation mechanisms are defined for the retrieved documentation content.
  • [CREDENTIALS_UNSAFE]: The SKILL.md file contains a hardcoded Algolia API key (3e42dbd4f895fe93ff5cf40d860c4a85) and Application ID (PLSDUOL1CA). These appear to be public search-only credentials intended for accessing the Remotion documentation index.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 02:18 PM
Security Audit — agent-trust-hub — remotion-docs