error-diagnostics-smart-debug
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data (error messages, stack traces, reproduction steps) via the
$ARGUMENTSvariable. - Ingestion points: The
$ARGUMENTSplaceholder is used to ingest external data in theContextsection and at the bottom of the skill definition. - Boundary markers: There are no delimiters or specific instructions to ignore embedded commands within the user-provided content, which could allow an attacker to influence the agent's behavior through crafted error logs.
- Capability inventory: The skill instructs the agent to use a
debuggersubagent and interact with various external observability platforms (e.g., Sentry, DataDog, ELK). - Sanitization: The instructions do not include any steps for sanitizing or validating the content of the
$ARGUMENTSinput before processing.
Audit Metadata