stakeholder-intel
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or security risks were identified in the skill. The instructions are purely functional and alignment-focused.
- [NO_CODE]: The skill does not include any scripts, commands, or software dependencies. It operates entirely as a structured prompt for the AI agent.
- [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection because it is designed to process untrusted external data (emails, Slack threads, transcripts). However, since the skill lacks any associated capabilities—such as network access, file system writing, or code execution—the risk of harmful outcomes is negligible.
- Ingestion points: SKILL.md (Inputs section: raw notes, emails, Slack threads, transcripts)
- Boundary markers: Absent (no explicit instructions to disregard embedded commands in the source data)
- Capability inventory: None (the skill has no code or tool-use definitions)
- Sanitization: Absent (the skill does not define methods for filtering or escaping input data)
Audit Metadata