to-tickets
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches context from user-provided references, including specification paths, issue numbers, and external URLs from well-known services like GitHub and Linear.
- [COMMAND_EXECUTION]: References the use of external developer tools such as
gh-stackfor branch management and utilizes configuration commands like/setup-matt-pocock-skillsfor environment setup. - [PROMPT_INJECTION]: Ingests potentially untrusted data from external sources (issue bodies, comments, and URLs), which represents an indirect prompt injection surface.
- Ingestion points: The context gathering step in
SKILL.mdinvolves fetching content from external references. - Boundary markers: No specific delimiters or "ignore previous instructions" warnings are provided for the ingested external content.
- Capability inventory: The skill can write local markdown files to the
.scratch/directory and perform network operations to publish issues on external trackers. - Sanitization: No explicit validation or sanitization of the fetched external content is defined within the skill instructions.
Audit Metadata