The Agent Skills Directory

[NO_CODE]: The skill is comprised solely of markdown instructions and YAML metadata. It does not include any scripts, binaries, or other executable components.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (procurement files, contracts, and evidence), creating a potential surface for indirect prompt injection. Ingestion points: External procurement and contract documents provided by the user as per the argument-hint. Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the analyzed documents. Capability inventory: The skill has no code execution, network access, or file-writing capabilities. Sanitization: There is no evidence of sanitization or filtering for external content before processing.\n- [SAFE]: The instructions are professional, focused on legal compliance, and consistent with the stated purpose. No malicious patterns such as prompt injection, obfuscation, or unauthorized data access were identified.

contract-performance