crm-cleanup

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from a CRM system that could potentially contain malicious payloads designed to influence agent behavior.
  • Ingestion points: Data is retrieved from the ~~crm connector, including deal details, contact information, and notes (SKILL.md).
  • Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore instructions embedded within the CRM data.
  • Capability inventory: The skill is granted access to the Bash, WebFetch, and Read tools, which could be abused if an injection is successful (frontmatter).
  • Sanitization: The skill mitigates risks through mandatory "approval gates," requiring explicit user confirmation for every modification and using side-by-side diffs for review (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 04:25 PM
Security Audit — agent-trust-hub — crm-cleanup