The Agent Skills Directory

[SAFE]: The skill does not contain any executable scripts, remote code execution patterns, or hardcoded credentials. It relies on standard agent capabilities to read the repository and write to a ticket tracker.- [PROMPT_INJECTION]: The skill processes 'current conversation context' which is a surface for indirect prompt injection. Malicious instructions provided by a user during the conversation could influence the synthesized specification published to the ticket tracker. Ingestion points: conversation context in SKILL.md. Boundary markers: absent. Capability inventory: repository exploration and ticket tracker publishing. Sanitization: absent.

to-spec