github-issue-creator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (such as error logs, raw notes, and voice dictation) which could contain malicious instructions designed to influence the agent's behavior during the conversion process.
- Ingestion points: Processes user-provided text input, logs, and screenshots described in
SKILL.md. - Boundary markers: The provided output template does not include specific boundary markers or instructions to ignore potential commands embedded within the input data.
- Capability inventory: The skill instructs the agent to create markdown files in the
/issues/directory. - Sanitization: The skill includes a specific security guideline to use placeholders (e.g.,
[PROJECT_NAME],[USER_ID]) for sensitive data, which mitigates data exposure but does not prevent instruction injection.
Audit Metadata