pinboard-manager
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto interact with the Pinboard API and the Jina Reader service. - [EXTERNAL_DOWNLOADS]: Fetches bookmark data from
api.pinboard.inand website content fromr.jina.ai. Both are well-known services for their respective purposes. - [PROMPT_INJECTION]: The 'Timeliness Check Mode' presents an indirect prompt injection risk.
- Ingestion points: External content is fetched from arbitrary URLs via the Jina Reader service (Step 3).
- Boundary markers: There are no explicit delimiters or instructions to the LLM to ignore potentially malicious commands embedded within the fetched bookmark content.
- Capability inventory: The skill has the capability to delete bookmarks (
/posts/delete) and update bookmark tags (/posts/add) based on the AI's assessment of the fetched content. - Sanitization: No evidence of sanitization or content filtering is provided before the external data is passed to the AI for analysis.
Audit Metadata