The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted project data, creating a potential vector for indirect prompt injection.
Ingestion points: The skill monitors and reads modified code files, dependency manifests, and configuration files via the Read and Grep tools (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between its own operational instructions and the potentially malicious instructions contained within the code it scans.
Capability inventory: The skill is configured with access to Read, Grep, and Bash tools, which could be misused if the agent is successfully manipulated by content in the scanned files (SKILL.md).
Sanitization: The skill does not implement sanitization or filtering of the code content before it is processed by the agent's logic.

security-auditor