values-behavioral-interview

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by design, as it ingests and processes untrusted user-supplied career stories. A maliciously crafted story could potentially contain instructions that leverage the agent's 'Write' and 'Edit' capabilities to perform unauthorized file modifications. * Ingestion points: User-provided career stories and story bank templates processed via the 'Read' tool in SKILL.md. * Boundary markers: Absent; no specific instructions are provided to the agent to isolate or ignore instructions embedded within the user data. * Capability inventory: The skill specifies 'Read', 'Write', and 'Edit' permissions in the SKILL.md file. * Sanitization: Absent; the skill does not describe any validation or escaping mechanisms for the stories being reviewed.
  • [NO_CODE]: The skill consists entirely of instructional markdown and reference files. No executable scripts, binaries, or package dependencies are included in the skill package.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 06:13 PM