slopsift

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download and execution of the slopsift CLI tool from the public npm registry using package runners like npx or bunx. This is the primary functional mechanism of the skill and aligns with the author's provided documentation.
  • [COMMAND_EXECUTION]: The skill executes shell commands to perform prose linting on files within the target workspace. It includes security best practices such as quoting globs to prevent unintended shell expansion and injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for indirect prompt injection by reading and analyzing untrusted prose from files in the repository.
  • Ingestion points: Reads Markdown, documentation, and source code files from the repository root (SKILL.md).
  • Boundary markers: Lacks explicit delimiters or ignore-instructions for the content being linted.
  • Capability inventory: Accesses shell execution and file modification tools.
  • Sanitization: Does not specify sanitization for the content processed by the linter.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 06:05 PM
Security Audit — agent-trust-hub — slopsift