reels-scripting
Warn
Audited by Snyk on Apr 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly scrapes and downloads Instagram Reels via Apify (Step 3) and follows Notion pages via WebFetch to locate Reel URLs (Step 1), then requires the agent to transcribe and analyze that untrusted, user-generated content with Gemini and use the analysis to generate scripts (Steps 4–5), so third-party content is ingested and directly influences tool use and decisions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill invokes Apify actors at runtime (e.g., apify/instagram-reel-scraper and apify/instagram-scraper via the Apify API) to run remote scraper code and return video/scrape data that the skill requires and uses as inputs to its analysis pipeline.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata