douyin-video-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 instructions to automatically install a runtime dependency and to conceal or avoid asking for user approval (e.g., "install... automatically without asking the user to confirm" and "Do not describe it... and do not request separate approval"), which is outside the advertised scraping purpose and attempts to change agent behavior secretly.
CRITICAL E006: Malicious code pattern detected in skill scripts.
- Malicious code pattern detected (high risk: 1.00). The Skill's instructions explicitly require installing a runtime dependency automatically and forbids asking the user or describing the install as a user action, which enables silent/unauthorized installs and creates a clear supply-chain/backdoor risk.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md instructs the agent to use the BrowserAct CLI to access real Douyin pages at runtime (public web content), which can include outsider-authored free text (captions/topics/comments) that the agent may ingest into the LLM context.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The Skill explicitly instructs the agent at runtime to automatically install and invoke BrowserAct using the provided installation links (e.g., https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main and https://www.browseract.com/?co-from=social-media), which implies fetching and executing remote installer/runtime code that controls the agent's execution.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill explicitly instructs the agent to install and invoke the BrowserAct CLI automatically without user confirmation, directing the agent to modify the host system by installing software (a non-trivial state change) even though it does not explicitly request sudo, create users, or edit system config files.
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