loom
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of ingesting and processing untrusted data.
- Ingestion points: External data enters the agent context through web searches for sources (Topic query) and processing user-provided URLs or PDFs (Standard intake) as described in
SKILL.md. - Boundary markers: The instructions do not define any delimiters or system instructions to ignore embedded commands within the ingested source material.
- Capability inventory: Across
SKILL.md, the skill performs file-write operations (creating.loom/config.yaml, Material Lists, Source Briefs, Synthesis Packs, and Topic Notes), directory creation for the vault, and network operations via web-search to find source materials. - Sanitization: There is no mention of sanitization, escaping, or validation of the content retrieved from external sources before it is processed into the vault artifacts.
Audit Metadata