slack-user-context
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from Slack history.
- Ingestion points: The skill reads from Slack DM history (im:history) and public channel searches (search:read.public) as documented in SKILL.md.
- Boundary markers: No boundary markers or 'ignore' instructions are present to prevent the agent from obeying instructions embedded in Slack messages.
- Capability inventory: The skill integrates with pyATS and slack-network-alerts, which can perform network actions and communications.
- Sanitization: The description does not mention any sanitization or validation of the external Slack content.
- [NO_CODE]: The skill consists exclusively of the SKILL.md file and does not include any Python or JavaScript code files.
Audit Metadata