bestblogs-read

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the bestblogs CLI tool to fetch resource data and update read status. This command execution is the primary mechanism for the skill's functionality.
  • [DATA_EXFILTRATION]: The skill notifies the BestBlogs service when a resource is read ('mark read'). This is a documented interaction with the vendor's own infrastructure and does not involve sensitive user information.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by processing external markdown content.
  • Ingestion points: External resource content (metadata and markdown) is retrieved from the BestBlogs API via the CLI as described in SKILL.md.
  • Boundary markers: The skill does not explicitly instruct the agent to use boundary markers or to ignore instructions contained within the fetched content.
  • Capability inventory: The skill's capabilities are focused on executing the bestblogs CLI to read and mark content.
  • Sanitization: There is no mention of sanitizing the fetched markdown content before it is presented to the LLM context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 07:31 AM
Security Audit — agent-trust-hub — bestblogs-read