review-resume

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is composed entirely of natural language instructions in markdown format. It does not include any scripts (e.g., Python, JavaScript), executables, or configuration files that perform operations on the host system.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data provided through the $RESUME and $JOB_POSTING variables. This creates a surface for indirect prompt injection where a malicious resume could attempt to manipulate the agent's behavior.
  • Ingestion points: Untrusted data enters the agent context via $RESUME and $JOB_POSTING (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or specific isolation commands to separate user data from system instructions.
  • Capability inventory: None. The skill does not use any tools, shell commands, or file system operations.
  • Sanitization: Absent. No validation or filtering is applied to the input variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 01:27 PM
Security Audit — agent-trust-hub — review-resume