ps-figure-it-out
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external artifacts (codebases, configurations, and system states) which presents a standard attack surface for indirect prompt injection.
- Ingestion points: The workflow instructions require the agent to read the "pre-change state" of artifacts and inspect the "real product" during verification phases (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined in this high-level playbook.
- Capability inventory: The skill orchestrates several other tools (ps-architect, ps-show-me-your-work) to modify the filesystem and generate logs, but contains no direct script execution itself.
- Sanitization: There are no provisions for sanitizing or escaping the content of artifacts analyzed during the workflow.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration. It does not include or distribute any executable scripts or binary files.
- [SAFE]: The skill implements safety-oriented patterns such as human-auditable logging ("Phase D: Keep the audit trail") and mandatory verification loops. All referenced tools and principles (ps-*) align with the author's established resource namespace.
Audit Metadata