Issue to PR Planner
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a systematic process for planning software changes based on issue descriptions. Analysis of the instructions and examples reveals no malicious intent, obfuscation, or unauthorized actions. The skill's operations are restricted to reading codebase files for context and producing textual implementation plans, which aligns with its stated purpose as a productivity tool. No hardcoded credentials, malicious network requests, or persistence mechanisms were found.
- [PROMPT_INJECTION]: The skill processes external issue text, representing a potential surface for indirect prompt injection. This is a characteristic of the skill's intended use case and does not present a high risk as the skill only generates a text-based plan.
- Ingestion points: User-provided GitHub issue text (SKILL.md).
- Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings for the input text.
- Capability inventory: Reading local codebase files to identify relevant files and patterns (SKILL.md, Step 2).
- Sanitization: Not present; the agent is instructed to read the issue thoroughly without explicit sanitization steps.
Audit Metadata