amazon-working-backwards

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates untrusted user data into its prompt instructions, creating a surface for indirect prompt injection.
  • Ingestion points: User input is passed via the $ARGUMENTS variable into the <context> block in SKILL.md.
  • Boundary markers: The template uses <context> tags to delimit user data from instructions.
  • Capability inventory: The skill does not explicitly invoke external tools or scripts, though the environment does not restrict tool access via the YAML frontmatter.
  • Sanitization: No sanitization is applied to the $ARGUMENTS content before it is interpolated into the model prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 10:28 AM
Security Audit — agent-trust-hub — amazon-working-backwards