remove-ai-slop
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external, potentially untrusted content from git diffs and surrounding code files, creating a surface for indirect prompt injection.
- Ingestion points: The skill uses
git diff,git diff --cached, and file reads to inspect the change set as described inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat content within diffs as data rather than instructions.
- Capability inventory: The skill is authorized to modify files in 'Fix' mode and run validation commands (e.g., test suites) after edits, which could be exploited if malicious instructions are embedded in the analyzed code.
- Sanitization: The skill lacks sanitization or validation logic for the content extracted from the git environment before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the local repository and validate changes.
- Evidence: The instructions explicitly direct the agent to run
git status,git diff, and 'validation' commands after making edits.
Audit Metadata