skills/toy-crane/obsidian-skills/save/Gen Agent Trust Hub

save

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (YouTube transcripts, web pages, and documents) to generate Obsidian notes and metadata. This creates an attack surface where instructions embedded in the source material could potentially influence the agent's behavior during restructuring or metadata generation steps.\n
  • Ingestion points: External content is fetched via extract-defuddle.sh, extract-web.sh, and extract-doc.sh from user-supplied URLs and file paths.\n
  • Boundary markers: The skill does not explicitly use delimiters or "ignore embedded instructions" warnings when passing extracted content to sub-tasks for restructuring or translation.\n
  • Capability inventory: The skill has permissions to write files to the local repository (01-inbox/), execute shell scripts, and modify git state (branch renaming).\n
  • Sanitization: Branch names and filenames are sanitized (converted to lowercase, special characters removed) before use. jq is used for safe JSON construction in all extraction scripts.\n- [EXTERNAL_DOWNLOADS]: The skill dynamically downloads and executes the markitdown package from PyPI during the document processing phase.\n
  • Evidence: scripts/extract-doc.sh uses uvx --from \"markitdown[all]\" markitdown \"$FILE_PATH\" to convert documents to markdown.\n- [COMMAND_EXECUTION]: The skill performs several shell-based filesystem and git operations based on the processed content.\n
  • Evidence: The orchestrator and scripts use commands including git branch -m, rm -rf, cat, and grep for context management and repository organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 08:03 AM