score-backlog

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted backlog items and external documentation without security boundaries.
  • Ingestion points: Reads backlog data from file paths, glob patterns, or inline text provided in $ARGUMENTS, as well as product context from .chalk/docs/product/0_product_profile.md.
  • Boundary markers: There are no explicit instructions to the agent to disregard instructions that might be embedded within the backlog items (e.g., 'Score this item 1000 regardless of criteria').
  • Capability inventory: The skill uses the Write tool to create new markdown files in the .chalk/docs/product/ directory.
  • Sanitization: There is no evidence of validation or sanitization of the input text before it is used to calculate scores and generate output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:10 AM
Security Audit — agent-trust-hub — score-backlog