Skills
Navigate
skills/jeremylongshore/tons-of-skills-marketplace/clari-security-basics/Gen Agent Trust Hub

clari-security-basics

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a python function redact_pii intended to process external data (forecast entries), creating a surface for indirect prompt injection if the source data is attacker-controlled.\n
  • Ingestion points: The entries list processed by the redact_pii function in SKILL.md.\n
  • Boundary markers: None identified for the data entries.\n
  • Capability inventory: The skill allows use of Read, Write, Edit, and Grep tools as defined in the frontmatter.\n
  • Sanitization: The provided code performs PII redaction via hashing but does not include sanitization against prompt injection attacks embedded in the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 01:17 PM