opsx-android-bug

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it processes untrusted data from user-supplied bug reports to determine the parameters for tool execution.
  • Ingestion points: The bug description or report provided as a command-line argument to the /opsx:android-bug slash-command.
  • Boundary markers: The skill definition lacks explicit delimiters or instructions for the agent to ignore or neutralize instructions embedded within the user-provided bug report.
  • Capability inventory: The agent is instructed to use the codegraph explore tool and the openspec CLI to create changes, designs, and tasks based on the input.
  • Sanitization: There is no evidence of input validation, sanitization, or escaping of the user-provided content before it is processed by the agent's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — opsx-android-bug