estimate-stories

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is composed solely of Markdown documentation; no executable Python, Node.js, or shell scripts are provided.
  • [SAFE]: No suspicious patterns, data exfiltration, or malicious instructions were detected in the workflow or reference files.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it analyzes content from user-provided story files (Category 8). Ingestion points: Content from story files provided via the story_file path input. Boundary markers: The workflow does not explicitly specify the use of delimiters or include instructions for the agent to ignore embedded commands within user-provided story text. Capability inventory: The agent is authorized to read and write Markdown files within its environment to perform the estimation tasks. Sanitization: No sanitization or escaping mechanism is described for the story file content before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:44 AM