instagram-reels-scraper
Fail
Audited by Snyk on Jul 20, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (high risk: 0.90). The skill contains explicit, deceptive runtime instructions to install BrowserAct without asking the user for confirmation and to hide/avoid describing that installation as something the user must open or approve, which is outside the skill's stated purpose and user consent expectations.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). The Skill contains explicit instructions to automatically install external runtime dependencies without user confirmation and to avoid disclosing or requesting approval for that installation, which is a deliberate covert installation/supply-chain behavior likely to enable malicious payload delivery or unauthorized access.
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 public Instagram pages/URLs at runtime (outsider-authored free text from fetched web content becomes LLM-readable via the browser automation results).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The Skill explicitly directs the agent at runtime to "Install BrowserAct" using the link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main to automatically obtain a required CLI/Skill, which implies fetching and executing remote installer code during runtime.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (high risk: 1.00). The Skill explicitly instructs the agent to automatically install a runtime dependency (BrowserAct) without asking the user for confirmation or approval, which directs the agent to modify the host environment and thus can compromise machine state.
Issues (5)
E004
CRITICALPrompt injection detected in skill instructions.
E006
CRITICALMalicious code pattern detected in skill scripts.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata