community-pulse
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text data from Discord messages to perform theme analysis and identify unanswered questions.
- Ingestion points: Discord message content retrieved via
mcp__cogny__discord__get_channel_messagesas described in Step 5 and Step 7. - Boundary markers: The instructions do not specify the use of structured delimiters or explicit boundary markers when interpolating message content into the agent's context.
- Capability inventory: The skill is granted access to
Writeandmcp__cogny__create_finding(a vendor-specific tool) in theallowed-toolsconfiguration inSKILL.md. - Sanitization: The instructions mandate anonymizing contributors and limiting displayed content to the first sentence, which serves as a mitigation measure against processing malicious payloads in full.
Audit Metadata