testing-perf
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing source code to generate performance tests, creating an attack surface where instructions embedded in processed data could influence the agent.\n
- Ingestion points: The agent is instructed to read local project files and test suites using tools like
Read,Glob, andGrep(e.g., inrules/execution.md).\n - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are defined in the instructions for the data being processed.\n
- Capability inventory: The agent has access to potentially sensitive capabilities including
WebFetchand file system read tools.\n - Sanitization: The skill lacks explicit guidance on sanitizing or escaping content from ingested files before it is included in the agent's context or output.
Audit Metadata