pinboard-manager

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Employs curl to interact with the official Pinboard API (api.pinboard.in) for reading, updating, and deleting bookmarks as part of its core bookmark management functionality.
  • [EXTERNAL_DOWNLOADS]: Utilizes Jina Reader (r.jina.ai), a well-known service, to fetch the content of bookmarked URLs for timeliness analysis. This enables the agent to evaluate the current relevance of technical articles.
  • [PROMPT_INJECTION]: Exhibits a vulnerability surface for indirect prompt injection because it processes untrusted content from the web and uses it to drive actions like bookmark deletion. 1. Ingestion points: Bookmarked web content is fetched via Jina Reader and provided to the agent in SKILL.md. 2. Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the fetched content are present in the analysis logic. 3. Capability inventory: The skill has the capability to delete bookmarks and update tags via the Pinboard API using curl. 4. Sanitization: No sanitization or filtering of the external content is performed before it is analyzed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 11:59 AM