think-premortem
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation, instructions, and templates. It does not contain any executable scripts (.py, .js, .sh), binary files, or dynamic commands that could be executed on a host system.
- [METADATA_POISONING]: Metadata fields in the YAML frontmatter and the
skill.meta.ymlsidecar are used correctly for classification and lineage tracking. There are no deceptive instructions or hidden commands in the metadata fields. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided decisions or plans. While it lacks explicit boundary markers for this untrusted input, the skill possesses no dangerous capabilities (such as network access, file-system modification, or code execution) that could be leveraged by an attacker-controlled input.
- [DYNAMIC_CONTEXT_INJECTION]: No use of shell-execution placeholders (
!command) was detected in the SKILL.md or any supporting files.
Audit Metadata