to-tickets
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs and codebase files to generate tickets.\n
- Ingestion points: External URLs, issue tracker bodies/comments, and local codebase files specified by the user in the context gathering phase.\n
- Boundary markers: None identified; the instructions do not define delimiters to separate instructions from the fetched external context.\n
- Capability inventory: The skill allows the agent to read local files, write local files to the
.scratch/directory, and interact with external trackers like GitHub or Linear.\n - Sanitization: The skill lacks instructions for sanitizing fetched content or ignoring embedded directives within the data.\n- [COMMAND_EXECUTION]: The skill relies on file system interaction to analyze the project and save ticket data.\n
- Evidence: Instructions direct the agent to "explore the codebase" and write individual files for each ticket under the
.scratch/directory.
Audit Metadata