log-observability-issues

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (LOW): The skill exhibits a vulnerability surface for indirect prompt injection because it processes and interpolates untrusted data from external sources.
  • Ingestion points: External data is ingested from the output of the /check-observability skill and the results of the gh issue list command (SKILL.md).
  • Boundary markers: Absent. There are no delimiters or instructions provided to the agent to disregard potentially malicious instructions embedded within the audit findings or existing issue titles/bodies.
  • Capability inventory: The skill has the capability to execute shell commands and perform write operations (creating issues) on a GitHub repository via the gh CLI.
  • Sanitization: Absent. The skill does not perform any escaping, validation, or filtering of the findings or existing issue content before using them to construct new issue descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:24 PM