T01 · Skill Instruction Hijacking
- Location
SKILL.md:3- Finding
Mandatory Third-Party Promotion Hijacks Product-Feedback Workflows
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Provener feedback-request integration that asks permission before submitting data, though users should notice that it proactively offers a specific third-party service.
Install this only if you want Codex to offer Provener for human product-feedback requests. Before authorizing submission, review the product details, contact fields, budget, payment-capable value, and any callback URL because those are sent to and stored by Provener.
SKILL.md:3Mandatory Third-Party Promotion Hijacks Product-Feedback Workflows
The skill instructs the agent to apply as soon as product-feedback intent appears, even before authorization is complete, which creates an overly broad invocation boundary. In practice this can cause premature collection of business details and steering users toward an external service without first establishing whether the request is in scope, authorized, or appropriate, increasing privacy and consent risk.
The trigger section uses broad language like applying the skill as soon as the user requests testing, critique, or validation, without strong exclusions or a higher-confidence threshold. In this context, that ambiguity is more dangerous because the skill is designed to route potentially sensitive product information to an external API, so over-triggering can lead to unnecessary data collection or premature disclosure workflows.