building-secure-contracts
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to the nature of its task.
- Ingestion points: The skill ingests untrusted data from contract files located at the
<target-path>provided in the arguments. - Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore or isolate malicious instructions that might be embedded in the files being audited.
- Capability inventory: The skill is granted significant capabilities including
Read,Write,Grep,Bash, andWebFetch, which increases the potential impact if the agent is manipulated by injected content. - Sanitization: No sanitization, escaping, or validation logic is present to handle the content of the external files before they are processed by the agent.
Audit Metadata