skills/maragudk/fabrik/bluesky/Gen Agent Trust Hub

bluesky

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the bsky command-line utility to perform social media operations like posting and replying, which aligns with its documented functionality.
  • [PROMPT_INJECTION]: There is an indirect prompt injection surface because the skill involves processing repository data to create public posts. 1. Ingestion points: Content is derived from files and technical achievements within a repository (SKILL.md). 2. Boundary markers: No specific delimiters are implemented to separate external content from the post instructions. 3. Capability inventory: The skill allows data to be sent to an external service (Bluesky) via the bsky CLI. 4. Sanitization: The instructions include strict guidelines to avoid sensitive data and only operate on public repositories, mitigating potential risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 12:18 AM
Security Audit — agent-trust-hub — bluesky