remotion-docs
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [Hardcoded Credentials]: The skill contains an Algolia API key and application ID in the
SKILL.mdfile. These are used to query the Remotion documentation index. While search-only keys for public documentation are often intended for client-side use, hardcoding them is a security consideration to review.- [Indirect Prompt Injection Surface]: The skill's workflow involves fetching Markdown content fromremotion.dev. This introduces a potential surface for indirect prompt injection, where instructions embedded in the external documentation could influence agent behavior. - Ingestion points: Documentation URLs such as
https://www.remotion.dev/docs/*.mdas specified inSKILL.md. - Boundary markers: There are no instructions provided to the agent to treat this external content as untrusted or to ignore instructions embedded within it.
- Capability inventory: The skill does not explicitly define subprocess or file-write capabilities, but the agent will process the external text content.
- Sanitization: No explicit sanitization or validation of the fetched Markdown content is defined.
Audit Metadata