composio

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill explicitly forbids the exposure of credentials, tokens, or raw authentication material in SKILL.md.
  • [SAFE]: User consent is mandatory for software installation and destructive write operations as per instructions in SKILL.md and references/cli.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection.
  • Ingestion points: Ingests data from external SaaS services (GitHub, Slack, Email) as described in SKILL.md.
  • Boundary markers: No delimiters or ignore-instructions markers are present in SKILL.md.
  • Capability inventory: CLI command execution and local file access are available in references/cli.md.
  • Sanitization: No sanitization methods are specified for service data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 06:41 PM
Security Audit — agent-trust-hub — composio