SkillSpector · scout

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

reference/multi-engine-mode.md

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

reference/tri-engine-investigate.md

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

SKILL.md

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

reference/advanced-reproduction-triage.md

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

reference/perf-investigation.md

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

references/advanced-reproduction-triage.md

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

reference/5whys-rca.md

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

SKILL.md