pre-mortem

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided plan descriptions to generate risk analyses.
  • Ingestion points: User descriptions of implementation plans as prompted by Step 1 in SKILL.md.
  • Boundary markers: Absent; the skill does not define specific delimiters for user input or include instructions to ignore embedded directives.
  • Capability inventory: None. The skill is purely instructional markdown and does not invoke system tools, perform network operations, or write to the filesystem.
  • Sanitization: Absent; no validation or escaping is applied to the input text.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:19 PM
Security Audit — agent-trust-hub — pre-mortem