content-repurposer

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes bash scripts (scripts/setup.sh, scripts/repurpose.sh, etc.) to automate content transformation using standard CLI utilities like jq, curl, and pbcopy.
  • [EXTERNAL_DOWNLOADS]: The main script (repurpose.sh) allows fetching content from arbitrary URLs using curl, which introduces a potential Server-Side Request Forgery (SSRF) risk.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external content (URLs/files) and interpolating it into LLM prompts. Ingestion points: scripts/repurpose.sh reads from local files or fetches from URLs. Boundary markers: Triple dashes (---) are used around source content in the prompts. Capability inventory: Shell script execution, file system access, network fetching (curl), and clipboard manipulation (pbcopy). Sanitization: No sanitization or filtering is performed on external content before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 09:36 AM