bm-share

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXFILTRATION]: The skill facilitates the movement of note data between projects. This is the intended behavior and is secured by a mandatory confirmation step (Step 4) where the agent must show the user the content and destination and wait for approval. Targets are restricted to those defined in the user's local configuration.
  • [PROMPT_INJECTION]: The skill ingests and processes note content, representing an indirect prompt injection surface.
  • Ingestion points: Note content is retrieved from the primaryProject using the read_note tool in Step 2 of SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the note content.
  • Capability inventory: The skill uses the write_note tool to publish content to target projects.
  • Sanitization: No specific sanitization or filtering is applied to the note content before it is copied.
  • [COMMAND_EXECUTION]: The skill utilizes the read_note and write_note tools as expected for its project management functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 11:56 AM
Security Audit — agent-trust-hub — bm-share