remotion-docs

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill contains a hardcoded Algolia API key (3e42dbd4f895fe93ff5cf40d860c4a85) and Application ID (PLSDUOL1CA) in SKILL.md to facilitate documentation search. While this is a public search key, hardcoding credentials in instruction sets is a poor security practice.
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from the vendor's domain (remotion.dev) and performs search queries via Algolia (algolia.net). These are recognized as legitimate service and vendor resources.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches external Markdown documentation which is then processed as instructions for the agent's implementation workflow.
  • Ingestion points: Documentation page URLs identified via search results in SKILL.md.
  • Boundary markers: Absent; the instructions do not define delimiters or specific safety wrappers for the fetched external content.
  • Capability inventory: Network operations via HTTPS (GET and POST).
  • Sanitization: None; the agent is instructed to use the documentation content directly for implementation guidance.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 01:48 PM
Security Audit — agent-trust-hub — remotion-docs