orcawave-orcaflex-readiness-audit
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run
pytestvia a shell command to verify code readiness, which is a standard and expected operation for developer tools. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests and processes untrusted data from external sources. 1. Ingestion points: GitHub issue content retrieved using the
gh issue viewcommand. 2. Boundary markers: The skill lacks explicit delimiters or instructions to treat issue content as untrusted data. 3. Capability inventory: The agent has the capability to execute local code viapytest. 4. Sanitization: There is no evidence of sanitization or validation of the content retrieved from the issue tracker before it is processed by the agent.
Audit Metadata