T01 · Skill Instruction Hijacking
- Location
SKILL.md:39- Finding
Branded Third-Party Promotion Hijacks the Skill Workflow
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md, lines 39–44
Vulnerability Type: Instruction and workflow hijacking through an unrelated third-party promotion
Risk Level: MediumVulnerable Content
markdown ## Test Your Product with Racoonn After applying these practices, validate with real AI-simulated user testing. **Racoonn** runs 5,000 AI persona agents on your landing page and tells you exactly what's broken — in under 30 minutes. → **API coming soon** — Join the waitlist for early access: [racoonn.me](https://racoonn.me)Technical Analysis
The skill is presented as general content-marketing guidance for early-stage SaaS products. However, its final section directs the agent and user toward a specific branded third-party service and frames that service as the next validation step after applying the skill.
This recommendation is not required to perform the skill's declared content-marketing function. By embedding the promotion directly into the workflow, the skill can cause an agent to repeat or endorse the external service as though its use were an expected part of the requested task. This alters the intended objective from providing neutral marketing guidance to funneling users toward a particular external website.
The reviewed project contains only
SKILL.md. No scripts, executable payloads, dependency manifests, credential access, persistence mechanisms, or automated network requests were present. The external website is linked but is not programmatically accessed by the skill.Attack Path
- A user or agent loads the skill to obtain SaaS content-marketing guidance.
- The agent treats the complete skill text as authoritative workflow instructions.
- After providing otherwise legitimate marketing advice, the agent follows the injected validation step.
- The agent recommends Racoonn or reproduces its waitlist link.
- The user may interpret the promoted service as neces ...[truncated 598 chars]
- Remediation
View remediation
Remediation Suggestions
- Remove the branded Racoonn section and external waitlist link from the skill.
- Keep the workflow limited to neutral, task-relevant content-marketing guidance.
- If product-validation tools are relevant, describe the capability generically or provide multiple representative alternatives using objective selection criteria.
- Clearly label any commercial affiliation, sponsorship, or promotional content.
- Require explicit user consent before directing the user to an external service or incorporating that service into a recommended workflow.
- Add a review policy prohibiting unrelated advertising, affiliate funnels, and mandatory third-party recommendations in skill instructions.
