hiring-helper

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted external data in the form of job applications and resumes.
  • Ingestion points: Job applications are ingested via manual paste or file input as described in the evaluation framework in SKILL.md.
  • Boundary markers: Absent. The example evaluation prompt provided in SKILL.md does not utilize delimiters (e.g., XML tags or triple quotes) to isolate candidate data from the agent's instructions.
  • Capability inventory: None. The skill consists of Markdown instructions only and does not reference any scripts, network tools, or file-system writing capabilities.
  • Sanitization: Absent. There is no logic to filter or escape instructions embedded within the processed text.
  • [No Code] (SAFE): The skill does not contain any executable scripts, binary files, or package dependencies. All logic is contained within natural language instructions and templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 01:20 AM