board-meeting-prep
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: Comprehensive analysis of the skill's instructions, templates, and scripts revealed no evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted user data to generate board materials.
- Ingestion points: User-supplied financial metrics and CEO narratives processed in
SKILL.mdandtemplates/output-template.md. - Boundary markers: Absent. The templates do not utilize specific delimiters or instructions to prevent the agent from following commands embedded within the provided metrics or narratives.
- Capability inventory: The skill's capabilities are limited to text generation and a local validation script (
scripts/check-output.py). The script only reads a file to check for keywords and does not output the file content, significantly mitigating data exposure risks. - Sanitization: Absent. No input validation or escaping is implemented. The risk is classified as low/safe given the skill's specific use case.
Audit Metadata