The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's ticket-drafting process. 1. Ingestion points: The SKILL.md file instructs the agent to fetch and read the full body and comments of external URLs or issue references provided by the user in the context-gathering phase. 2. Boundary markers: The instructions do not define specific delimiters or 'ignore embedded instructions' warnings for the fetched content. 3. Capability inventory: The skill has the capability to write local files to the .scratch/ directory and explore the local codebase. 4. Sanitization: There is no mention of sanitization or validation of the fetched external content before it is processed.
[DATA_EXFILTRATION]: The skill performs network operations to retrieve data from external URLs or issue trackers provided as arguments. Evidence: SKILL.md contains instructions to 'fetch it and read its full body and comments' for references provided by the user.
[COMMAND_EXECUTION]: The skill instructions require the agent to 'explore the codebase' to understand the current state, which implies read access to the local project environment.

to-tickets