jelinek-writing
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, including GitHub issues, PR descriptions, and Slack messages.
- Ingestion points:
SKILL.mddescribes processing user-provided text from various sources like GitHub, Slack, and technical documentation. - Capability inventory: The skill performs text generation and revision. It does not utilize subprocesses, network operations, or file-writing tools.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the processed text.
- Sanitization: No specific sanitization or filtering of external content is mentioned.
Audit Metadata