The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources, which constitutes a vulnerability surface for indirect prompt injection attacks where malicious instructions could be embedded in project data.
Ingestion points: The instructions in SKILL.md, interview.md, map.md, and project.md direct the agent to read task bodies, completion claims, backlog items, design documents, and repository instructions.
Boundary markers: The skill lacks directives for the agent to use delimiters or specific warnings to ignore instructions embedded within the ingested data.
Capability inventory: The skill utilizes the agent's ability to read and write files, as well as interact with external task trackers and CLI tools.
Sanitization: No sanitization, validation, or filtering procedures are defined for the data retrieved from external sources before it enters the agent's context.

planning