The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface where it ingests data from untrusted project files and uses it to update documentation and system manifests.
Ingestion points: The skill processes local files such as AGENTS.md, requirement documents, specifications, and various source code files during the "Gather" phase defined in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious embedded content within the ingested files.
Capability inventory: The agent has the capability to read any file in the repository and write/update documentation files (.md) and project configuration files (like AGENTS.md and README.md).
Sanitization: There is no evidence of escaping or validation of the content read from external documents before it is used to populate templates or update files.

engineer