arcads-video-marketing

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to clone a repository from github.com/krusemediallc/arcads-claude-code.git and installs packages from public registries (NPM via npx, PyPI via pip).
  • [COMMAND_EXECUTION]: The installation process involves running a shell script (./scripts/setup.sh). Additionally, the skill utilizes subprocess.run to call local Python scripts for Meta ad publishing and uses system tools like ffmpeg and jq for video processing.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection (Category 8):
  • Ingestion points: User-provided creative prompts and data returned from the Arcads API (e.g., job results, video URLs) in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary markers are used to separate user/API content from instruction logic.
  • Capability inventory: The skill has the ability to execute shell commands (subprocess.run), perform network requests (requests.post), and write to the local filesystem (output/).
  • Sanitization: No explicit sanitization or validation of the API-returned content or user prompts is shown before being used in further processing steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 06:21 AM
Security Audit — agent-trust-hub — arcads-video-marketing