The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it incorporates external data from the current conversation and repository files into its output generation process.
Ingestion points: Conversation history and project instruction files such as AGENTS.md or CLAUDE.md.
Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are present in the skill's instructions.
Capability inventory: Repository exploration, file writing to the OS temp directory, and publishing to external issue trackers as defined in SKILL.md.
Sanitization: None described.
[COMMAND_EXECUTION]: The skill directs the agent to interact with the file system by writing output to the operating system's temporary directory and potentially performing network operations to interact with issue trackers.

to-spec