The Agent Skills Directory

[SAFE]: The skill documents procedural use of internal search tools (search, code_search, read_document). It contains no executable code, no unauthorized network requests, and no attempts to access sensitive system credentials.\n- [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface because it reads and processes data from external sources (enterprise documents and code repositories).\n
Ingestion points: Data retrieved through search, code_search, and read_document tools as described in SKILL.md.\n
Boundary markers: Absent; the instructions do not define specific delimiters to wrap or identify potentially untrusted document content.\n
Capability inventory: The skill uses tools for reading enterprise data; it does not contain capabilities for arbitrary command execution, file system modifications, or data exfiltration.\n
Sanitization: Absent; the workflow does not include instructions for the agent to sanitize or validate the content of the documents it reads before synthesis.

plan-prep