openai-researcher
Warn
Audited by Snyk on Apr 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's §5 Platform Support explicitly instructs the agent to "Read [URL] and install as skill" pointing to the public raw GitHub URL (https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/openai/openai-researcher/SKILL.md), which causes the agent to fetch and ingest external, user-hosted content that can modify its system prompt/behavior and thus enable indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs platforms to "Read [URL]" at runtime—fetching https://raw.githubusercontent.com/theneoai/awesome-skills/main/skills/enterprise/openai/openai-researcher/SKILL.md would load the skill's system prompt/instructions and therefore directly control the agent at runtime, making it a required external dependency.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata