skills/zocomputer/skills/lastfm/Gen Agent Trust Hub

lastfm

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute curl and jq commands to interact with the Last.fm API and process the returned JSON data.
  • [EXTERNAL_DOWNLOADS]: Fetches music metadata and user history from Last.fm's official API (ws.audioscrobbler.com). This is expected behavior for the stated purpose of the skill.
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified where external data is ingested.
  • Ingestion points: Data entering the agent context via curl requests to the Last.fm API endpoints (SKILL.md).
  • Boundary markers: Absent. The skill does not provide delimiters or warnings to ignore instructions that might be embedded in music metadata (e.g., track titles or artist bios).
  • Capability inventory: Subprocess calls via curl for network GET operations and jq for data transformation.
  • Sanitization: Absent. The external content is interpolated directly into the agent's context without escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 07:32 AM