Skills
Navigate
skills/borghei/claude-skills/social-content/Gen Agent Trust Hub

social-content

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured marketing guidelines and utility scripts for engagement calculation, hashtag analysis, and post scheduling.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains scripts that ingest user-provided data, such as post text for hashtag analysis and JSON files for engagement metrics.
  • Ingestion points: scripts/hashtag_analyzer.py (via text input or --file), scripts/engagement_calculator.py (via posts.json), and scripts/post_scheduler.py (via --config JSON).
  • Boundary markers: The Clarify First section in SKILL.md provides explicit verification steps for the agent to follow before generating content.
  • Capability inventory: The scripts are limited to local file reading and console output. They do not perform network operations, write to the filesystem, or execute subprocesses.
  • Sanitization: The scripts use standard JSON parsing and regex-based extraction (re.findall) which limits the potential for control-flow manipulation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — social-content