trakt

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the 'trakt-cli' package from the NPM registry to interact with Trakt.tv, a well-known media tracking service (SKILL.md).- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data.
  • Ingestion points: Data enters the agent context through the output of 'trakt-cli history' and 'trakt-cli search' commands, which fetch metadata from the Trakt.tv API (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or warnings to separate API-sourced content from agent instructions.
  • Capability inventory: The agent has the capability to execute shell commands ('trakt-cli') to interact with the local filesystem and network.
  • Sanitization: There is no evidence of sanitization or filtering of the content returned from the external API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 05:37 AM
Security Audit — agent-trust-hub — trakt