The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from conversation context, codebase contents, and external issue tracker comments to synthesize specifications. Ingestion points: documentation/agents/issue-tracker.md and issue comments. Boundary markers: None provided to delimit untrusted input from synthesis logic. Capability inventory: Repository exploration, local file drafting, and publication to external trackers. Sanitization: No explicit filtering or validation of external content is performed.
[COMMAND_EXECUTION]: The skill directs the agent to perform broad repository exploration and file system modifications to resolve destinations and publish records, creating a capability surface that can be targeted by injected content.

to-specifications