url-scrape

Fail

Audited by Snyk on Jun 15, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.90). The set includes a direct raw.githubusercontent.com URL that the skill downloads and executes as a shell script (a high-risk pattern from an unverified GitHub account), plus wildcard/ambiguous URLs (http://, https://, bare https://) that could point to arbitrary hosts—together these indicate a suspicious download source because they enable automatic execution of remote code from an untrusted repository.

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

  • Third-party content exposure detected (high risk: 0.95). The skill ingests outsider-authored free text from the user-supplied URL: scripts/scrape_url.sh passes the URL to the local tool frevana_scrape, which fetches and converts the remote page content (public web content) into readable Markdown that is then printed/returned to the agent.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).


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

  • Attempt to modify system services in skill instructions detected (high risk: 0.80). This skill explicitly requires downloading and executing a remote setup.sh that can install the Frevana binary and start a local daemon (and thus modify the system state and potentially invoke privileged actions like installing software), so it directs changes to the host system and may require elevated rights.

Issues (4)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jun 15, 2026, 03:38 AM
Issues
4
Security Audit — snyk — url-scrape