extract-entities

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from various text artefacts to drive its entity extraction and file creation workflow.
  • Ingestion points: Target files or text snippets provided to the Read tool as described in the 'Workflow' section.
  • Boundary markers: The instructions lack explicit delimiters or guidance for the agent to ignore instructions embedded within the source text.
  • Capability inventory: The skill uses Write and Edit tools to modify the local filesystem at ~/.claude/memory/KNOWLEDGE/.
  • Sanitization: There is no mention of sanitizing or validating the extracted content before writing it to the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 08:09 PM
Security Audit — agent-trust-hub — extract-entities