pd-slack-threads
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill retrieves and processes text from Slack messages and threads, which are untrusted external data sources.
- Ingestion points: Slack message text and thread metadata processed via resources/pd-slack.ts as invoked in SKILL.md.
- Boundary markers: No explicit delimiters or instructions were found to isolate the untrusted Slack content from the agent's core instructions.
- Capability inventory: The skill has the capability to execute local scripts via npx tsx.
- Sanitization: There is no evidence of sanitization, filtering, or escaping of the incoming Slack data in the provided skill definition.
Audit Metadata