rrwrite-extract-figures-tables

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing data from external, untrusted repositories.
  • Ingestion points: Untrusted data is ingested from the path specified by the --repo_path argument (SKILL.md).
  • Boundary markers: The instructions lack explicit boundary markers or instructions to the agent to ignore embedded commands within the analyzed repository files.
  • Capability inventory: The skill has the capability to write files to the local disk and execute scripts via the Bash tool (SKILL.md).
  • Sanitization: There is no mention of sanitizing or validating repository content, such as file names or table data, before including it in the generated manifests or visualizations.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute local scripts and standard shell utilities.
  • Evidence: It executes python scripts/rrwrite-extract-figures-tables.py and python scripts/rrwrite_manifest_generator.py to perform extraction and validation tasks (SKILL.md).
  • Evidence: It uses the find command to manually search for figure files within the user-provided repository path (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 03:18 AM
Security Audit — agent-trust-hub — rrwrite-extract-figures-tables