diagnostic-issue-resolver

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run local system diagnostics (stat, pgrep, ls, tail) and executes maintenance scripts such as tts_read_clipboard_wrapper.sh, tts_stop.sh, and kokoro-install.sh. These operations are limited to the local environment and are necessary for the skill's stated purpose of resolving system locks and verifying engine health.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes local log files (/tmp/kokoro-tts.log, /tmp/tts_errors.log) which may contain fragments of text previously processed by the TTS engine from potentially untrusted sources.
  • Ingestion points: Log files located at /tmp/kokoro-tts.log and /tmp/tts_errors.log (referenced in SKILL.md and common-issues.md).
  • Boundary markers: None identified.
  • Capability inventory: Shell execution via the Bash tool and file reading via the Read and Grep tools.
  • Sanitization: Content is processed via tail and grep for diagnostic patterns; it is not directly interpolated into sensitive execution contexts or evaluated as code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 12:41 PM
Security Audit — agent-trust-hub — diagnostic-issue-resolver