repo-spring-cleaning
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it is designed to read and process the full contents of a repository, including code and documentation which are untrusted inputs.
- Ingestion points: The workflow in SKILL.md requires inspecting repository instructions, READMEs, manifests, lockfiles, and CI configurations.
- Boundary markers: There are no explicit instructions for the agent to treat repository content as data separate from its own operating instructions.
- Capability inventory: The skill utilizes file-writing capabilities to perform cleanup and command-execution capabilities to run validation scripts (Workflow steps 5 and 6).
- Sanitization: No explicit sanitization or filtering of the processed content is specified.
- [COMMAND_EXECUTION]: The workflow requires the execution of validation and test commands defined within the repository being audited. While this involves executing local scripts, it is a core function of a maintenance tool and is limited to documented project commands.
Audit Metadata