The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and test files, which serves as a potential vector for indirect prompt injection.
Ingestion points: The skill reads target files, caller functions, and test suites in SKILL.md (Step 1) using the Read, Glob, and Grep tools.
Boundary markers: There are no explicit delimiters or "ignore instructions" warnings defined for the content read from external files, which could allow malicious comments in the code to influence the agent's behavior.
Capability inventory: The skill has the ability to modify the filesystem using Edit and Write, and can execute shell commands via the Bash tool to run tests, type checks, or build steps in SKILL.md (Step 5).
Sanitization: The skill does not perform sanitization or validation of the ingested code content before it is processed or used as triggers for shell-based verification commands.

code-simplify