axiom-analyze-test-failures
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to run shell commands such as
ls,xcsym, andswift testto list crash reports, symbolicate them, and execute test suites. These are standard operations for development and debugging workflows. - [DATA_EXFILTRATION]: The agent is tasked with accessing and reading crash reports located at
~/Library/Logs/DiagnosticReports/. These files are necessary for diagnosing test failures but may contain sensitive system-specific metadata. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests and analyzes content from local source code files.
- Ingestion points: The agent scans files matching
*Tests.swift,*Test.swift, and**/*Tests/*.swiftas specified inSKILL.md. - Boundary markers: There are no instructions provided to the agent to use specific delimiters or to disregard potential instructions embedded within the analyzed test code.
- Capability inventory: The agent can execute shell commands (
xcsym,swift test,ls) and write suggested fixes back to the codebase based on the analyzed content. - Sanitization: The skill does not implement sanitization or validation of the code content before processing it.
Audit Metadata