The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted contract text, which serves as a potential surface for indirect prompt injection where malicious instructions could be embedded in the analyzed agreement.
Ingestion points: The scripts/contract_analyzer.py script reads contract files provided by the user.
Boundary markers: There are no explicit delimiters or safety instructions in the prompt or scripts to separate the untrusted data from the agent's instructions.
Capability inventory: The skill provides scripts for file system read and write operations; it does not possess network access, arbitrary code execution, or subprocess capabilities.
Sanitization: The tool performs analysis using regular expression pattern matching and does not execute the contract content as code.
[SAFE]: A thorough analysis of the skill's scripts and documentation revealed no indicators of malicious intent. The skill uses only standard Python libraries, contains no obfuscated strings, and does not attempt to access sensitive system files or credentials.

contract-review