skills/jonaskahn/specwright/sw-ingest/Gen Agent Trust Hub

sw-ingest

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/to_md.py script executes local utilities (such as tesseract and pandoc) using subprocess.run. These calls are safely implemented using argument lists and do not invoke a shell, protecting against command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted business evidence, which represents an indirect prompt injection surface.
  • Ingestion points: The scripts/to_md.py script reads and parses various file formats (PDF, CSV, HTML, Email, ZIP, etc.).
  • Boundary markers: The skill implements a INJECTION regex filter in scripts/to_md.py and instructions in SKILL.md to wrap suspicious content in block quotes, preventing the agent from executing embedded instructions.
  • Capability inventory: Capabilities include system command execution via subprocess.run (in scripts/to_md.py) and local file system writes (in scripts/to_md.py, scripts/impact.py, and scripts/secrets_scan.py).
  • Sanitization: The scripts/to_md.py script performs Unicode normalization and strips hidden control characters from all converted text.
  • [CREDENTIALS_UNSAFE]: The skill includes a dedicated scanner, scripts/secrets_scan.py, designed to detect and redact sensitive data like Atlassian tokens, AWS keys, and PII from ingested content. This proactive measure prevents the exposure of credentials within the agent's workspace.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 08:31 AM