write-high-signal-update
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a stylistic guide for generating high-signal status updates. Analysis of all files shows no evidence of command execution, network requests, sensitive file access, or obfuscation. The skill relies on local reference documents for plain language and voice preservation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (user status updates) to generate its output, which is a common surface for indirect prompt injection. The lack of impactful capabilities within the skill minimizes any potential risk.
- Ingestion points: User-provided text for status, decisions, or incidents mentioned in
SKILL.md. - Boundary markers: Absent.
- Capability inventory: No tools, file access, or network operations are invoked by the skill instructions.
- Sanitization: The skill does not perform validation or escaping of the user-provided content.
Audit Metadata