oodle-o11y-context

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by defining a structured manifest intended to be parsed from Pull Request descriptions, which are untrusted external inputs.
  • Ingestion points: PR descriptions retrieved via GitHub/Linear MCP or the gh CLI (SKILL.md).
  • Boundary markers: The manifest uses a specific header (## O11y Change Context) and structured key-value pairs which provide delimiters, but no explicit instructions are provided to the agent to ignore or sanitize embedded natural language instructions within the manifest values.
  • Capability inventory: The skill is designed to be used in conjunction with oodle-triage and oodle-o11y-review, which process this data to perform triage and review actions.
  • Sanitization: No sanitization, validation, or escaping of the external manifest content is defined.
  • [COMMAND_EXECUTION]: The skill documentation references the use of the gh CLI (gh pr list, gh pr view) to fetch pull request data when a dedicated MCP is unavailable. This is a standard and appropriate use of the command-line tool for the skill's stated purpose of managing PR context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:11 PM
Security Audit — agent-trust-hub — oodle-o11y-context