create-pr
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the repository to determine its actions.
- Ingestion points: The skill reads various repository files including
package.json,pyproject.toml,Makefile,CONTRIBUTING.md, and.cursor/rules/*to discover and run validation commands. - Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores malicious instructions that might be embedded in these project files.
- Capability inventory: The agent is authorized to execute shell commands (such as
npm,pip,go,make,git, andgh) and perform file system writes to fix findings. - Sanitization: The skill does not implement sanitization or validation logic for the commands it extracts from the repository configuration files.
Audit Metadata