instagram-profile-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The Skill contains explicit instructions to auto-install a runtime dependency and to hide that installation from the user ("without asking the user to confirm" and "Do not describe it... and do not request separate approval"), which are deceptive directives outside the scraping purpose.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). These links point to an unfamiliar third-party site (browseract.com) used to deliver a CLI installer and the skill instructs automatic installation without explicit user consent, which is a high-risk pattern for distributing executables/malware.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to use the BrowserAct CLI to access live Instagram/public web pages at runtime (outsider-authored free text from fetched web content), which can be ingested into the LLM context for extraction.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.90). The Skill instructs the agent to automatically install the BrowserAct CLI and treat it as a required runtime dependency "without asking the user to confirm" and "do not request separate approval for dependency installation," which directs the agent to modify the host system (install software) without user consent and could require elevated privileges.