The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search for and resolve comments (TODO/XXX) across the entire codebase. This creates a vulnerability where malicious instructions could be embedded in codebase comments to influence the agent's reasoning or code generation process.
Ingestion points: Codebase files containing TODO or XXX strings, retrieved via git grep.
Boundary markers: No delimiters or safety instructions are provided to distinguish between the comment's intent and potentially malicious instructions within the comment text.
Capability inventory: The agent is tasked with studying code, reasoning about solutions, and writing new code based on the content of these comments.
Sanitization: The skill lacks validation or sanitization steps to filter or escape the content of the comments before the agent processes them.

aisolve