skills/kkenny0/loom-skills/loom/Gen Agent Trust Hub

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
Risk Level
SAFE
Analyzed
May 27, 2026, 02:51 AM
Security Audit — agent-trust-hub — loom