Trakt Read-only
Analysis
The artifacts match a read-only Trakt.tv query skill, with the main caution being its documented use of Trakt credentials and optional OAuth secrets for playback/device-flow features.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
Use `{baseDir}/scripts/trakt-api.sh` ... `watching` ... `recent [limit]` ... `playback <type> <start_at> <end_at>` — playback progress (OAuth required)The skill gives the agent a local script for making external Trakt API calls. This is expected for the purpose and documented as read-only, but users should notice that the agent can invoke these Trakt-querying commands.
Source: unknown Homepage: none
The registry metadata does not provide an upstream source or homepage for provenance checking. The included script is still present for review and no remote installer is specified.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
TRAKT_ACCESS_TOKEN: "YOUR_TRAKT_OAUTH_TOKEN", // required for playback TRAKT_CLIENT_SECRET: "YOUR_TRAKT_CLIENT_SECRET" // required for device token exchange
The skill may use OAuth account secrets for playback and device-token exchange. This is disclosed and purpose-aligned, but these values are more sensitive than a public Trakt client ID.
