osint

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). This repo is an unvetted third‑party GitHub project that the skill explicitly instructs to clone, build, and run a native binary — executing unknown binaries from such sources is high risk and can deliver malware.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The repo is a high-risk OSINT toolkit explicitly designed for targeted profiling and automated harvesting of private/internal data (Telegram history, emails, breach lookups, scraping with CAPTCHA/auth bypass), including tooling to replay hidden API requests that can incorporate environment-held tokens — capabilities that readily enable privacy-invading data collection and targeted abuse.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md’s required runtime workflow performs OSINT web/social fetching (e.g., Phase 1/2 “web_fetch”/“jina.sh read”/“apify.sh …”/“brightdata.sh scrape” of arbitrary URLs and scraped page text), which is outsider-authored free text that can be ingested into the agent/LLM context via the Perplexity/Jina/other tool outputs and subsequent summarization.