Slack
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security issues detected. The skill defines a set of Slack API interactions using structured JSON schemas and examples.
- [NO_CODE]: The skill is composed entirely of markdown documentation and action definitions; no scripts, binaries, or executable code are included.
- [PROMPT_INJECTION]: No evidence of malicious prompt injection or behavior override patterns detected. The skill possesses an indirect prompt injection surface inherent to Slack tools: 1. Ingestion points: 'readMessages' action in SKILL.md. 2. Boundary markers: None. 3. Capability inventory: 'sendMessage', 'editMessage', 'deleteMessage', 'pinMessage', 'unpinMessage' actions in SKILL.md. 4. Sanitization: None. This surface is expected for the tool's functionality.
- [CREDENTIALS_UNSAFE]: No hardcoded secrets were found; the skill correctly requests a configuration object for authentication.
Audit Metadata