thinking-jobs-to-be-done
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a methodology for analysis rather than executing technical commands. It does not include any scripts, binaries, or configuration that could lead to malicious behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources such as PRDs, support tickets, and analytics logs. While these sources could theoretically contain malicious instructions, the skill has no exploitable capabilities; it lacks network access, file-writing permissions, and shell execution. Furthermore, the
disable-model-invocation: truesetting in the frontmatter prevents the agent from being coerced into calling other tools or models.
Audit Metadata