miniapp-devtools-recovery
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No attempts to override system prompts or bypass safety guardrails were found. The instructions are strictly focused on technical repository maintenance.
- [DATA_EXFILTRATION]: The skill does not request network access or the use of tools like curl or wget. It does not target sensitive file paths such as SSH keys or cloud credentials.
- [COMMAND_EXECUTION]: While the skill uses the Bash tool, its application is restricted by the instructions to repository inspection (git status) and standard file operations (deleting generated residue and restoring tracked files).
- [REMOTE_CODE_EXECUTION]: No patterns for downloading or executing remote scripts or packages were identified.
- [OBFUSCATION]: The content is clear and uses no encoding, hidden characters, or homoglyph techniques.
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository files which could theoretically contain malicious content, but its primary function is structural cleanup (moving/deleting files) rather than executing data as instructions.
Audit Metadata