The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data and existing project files to identify design inconsistencies, which creates an inherent attack surface for indirect prompt injection where malicious instructions could be embedded in the analyzed code.
Ingestion points: The feature argument and project source files discovered via search operations described in SKILL.md.
Boundary markers: The instructions lack explicit delimiters or warnings to the agent to ignore potentially malicious natural language instructions embedded within the code being analyzed.
Capability inventory: The skill utilizes file system search (grep) and file modification capabilities (replacing hard-coded values, deleting orphaned code, consolidating components).
Sanitization: No sanitization, validation, or escaping of the ingested content is specified before the agent processes the information.

normalize