section-logic-polisher
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
scripts/run.py) to perform logic checks and generate reports on document sections. - [DATA_EXPOSURE]: The skill reads workspace files including draft profiles, section files (
sections/*.md), and briefs (outline/*.jsonl) to perform its analysis. It does not perform any network operations. - [DYNAMIC_EXECUTION]: The checker script dynamically modifies the system path to import local modules (
tooling.common) by searching for a repository marker (AGENTS.md) in parent directories. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted content from subsection files and briefs, which could theoretically contain instructions designed to influence the agent's editing behavior.
- Ingestion points:
sections/S*.md,outline/subsection_briefs.jsonl, andoutline/writer_context_packs.jsonl. - Boundary markers: Absent; the skill does not specify delimiters for external content.
- Capability inventory: The agent has file-write access to update section files under the
sections/directory. - Sanitization: No explicit sanitization or instruction filtering is performed on the ingested text data.
Audit Metadata