The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from local files, creating a surface for indirect prompt injection if those files contain hidden instructions designed to manipulate the agent.
Ingestion points: Reads progress and memory data from docs/progress.md and the docs/memory/ directory.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing the file content.
Capability inventory: The skill performs file system read operations to extract and summarize content.
Sanitization: No evidence of sanitization, filtering, or escaping of the external file content before it is processed by the agent.

recap-context