jobs-digest
Fail
Audited by Snyk on Jun 17, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E005: Suspicious download URL detected in skill instructions.
- Suspicious download URL detected (high risk: 0.95). These are raw GitHub links to an install .sh and .ps1 that the skill tells users to pipe directly into bash/iex from an unverified GitHub account (solid-company) — a high-risk pattern because it allows execution of arbitrary, unreviewed code on the system.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow runs
sjctl sync --jsonandsjctl watch list/profile show, which (by design) fetches and processes job-offer data from external job sources at runtime; those offers are outsider-authored free text that the agent will ingest into the LLM context for ranking/digesting.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill may run installation commands at runtime that fetch and execute remote scripts—e.g., curl -fsSL https://raw.githubusercontent.com/solid-company/solid-jobs-skills/main/scripts/install-sjctl.sh | bash and irm https://raw.githubusercontent.com/solid-company/solid-jobs-skills/main/scripts/install-sjctl.ps1 | iex—so it relies on and executes remote code from those URLs.
Issues (3)
E005
CRITICALSuspicious download URL detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata