loom-maintain
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
scan_vault.py,validate_vault.py, andbuild_indexes.py) found in the../shared/scripts/directory to perform vault analysis. These scripts are invoked viapython3and include functionality to modify the local filesystem when requested. - [PROMPT_INJECTION]: The skill ingests untrusted Markdown data from the vault, creating an attack surface for indirect prompt injection.
- Ingestion points: Processes index files (
TIMELINE_INDEX.md,TOPIC_INDEX.md,CONNECTION_INDEX.md) and various Topic Notes. - Boundary markers: The skill does not employ delimiters or specific instructions to ignore embedded prompts in the vault content.
- Capability inventory: Access to local shell execution through Python scripts and file system write access.
- Sanitization: No sanitization or validation of the content read from the vault is specified.
Audit Metadata