content-marketing
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides bash script snippets that utilize
grepandsedto search for and modify text in files passed as arguments. These tools are used for "AI slop" detection and removing invisible Unicode watermarks (zero-width characters and BOM). - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to process and analyze external text files for quality scoring and cleaning.
- Ingestion points: File paths passed to the shell scripts via the
$1variable (e.g., ingrepandsedcommands). - Boundary markers: Absent; the scripts process the raw content of the provided files without explicit delimiters or instructions to ignore embedded commands.
- Capability inventory: Includes file reading and pattern searching via
grep, and in-place file modification viased -i. - Sanitization: No sanitization is performed on the input content before it is processed by the regex patterns or modification scripts.
Audit Metadata