opsx-trace-log
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied arguments (entry points, flow descriptions, or suspicions) to drive automated code exploration and instrumentation.
- Ingestion points: The skill ingests untrusted data directly from the argument provided after the
/opsx:trace-logcommand. - Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within the user input are defined.
- Capability inventory: The skill uses
codegraph exploreto navigate the codebase and performs file-write operations to add and remove instrumentation markers. - Sanitization: No sanitization or validation of the user-provided entry point is mentioned, which could allow an attacker to provide crafted inputs that manipulate the code exploration process.
- [COMMAND_EXECUTION]: The skill facilitates the execution of local development tools.
- Evidence: It explicitly mentions using the
openspec CLI,codegraph explore, andadb logcatfor capturing diagnostic information.
Audit Metadata