playbook-crisis-communications
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: Analysis of the skill's instructions confirms they are purely informational and procedural, focused on generating a crisis management document for client use. No malicious patterns or bypass attempts were detected.
- [NO_CODE]: The skill does not include any executable code, scripts, or system-level commands. It functions as a document generator using standard markdown text.
- [DATA_EXPOSURE]: The skill requests contact details (names and WhatsApp numbers) to populate placeholders in the playbook templates. This is a functional requirement for generating a crisis manual, and no evidence of data exfiltration or unauthorized access to system credentials was found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs such as client names and contact details to generate the playbook.
- Ingestion points: 'Required Input' section in SKILL.md.
- Boundary markers: Absent.
- Capability inventory: No file-write, network, or execution capabilities were identified in the skill.
- Sanitization: No explicit sanitization of input data is defined, but the lack of exploitable capabilities renders this surface benign.
Audit Metadata