T01 · Skill Instruction Hijacking
- Location
SKILL.md:8- Finding
Unconditionally Overrides Agent Role and Response Policy
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a simple coaching-style skill with broad behavior instructions, but it contains no code, persistence, credential access, data collection, or hidden execution.
Install this only if you want the assistant to default to a reflective coaching style. It may be less direct for normal factual or coding requests unless you explicitly ask for direct answers or disable the skill.
SKILL.md:8Unconditionally Overrides Agent Role and Response Policy
The skill is defined with a very broad behavioral scope ('turns the agent into Attention OS') and no clear activation boundaries, so it can reshape the assistant's behavior across many unrelated conversations. This increases the chance of prompt-scope overreach, where the skill overrides normal task expectations and injects opinionated guidance even when the user did not explicitly request that mode.
The file mandates a specific communication style in natural language regardless of user preference. This can be a policy concern when a skill imposes a fixed interaction mode without offering the user a choice or documenting that constraint as optional.