shaping-work

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external sources and incorporates it into agent-generated documentation.
  • Ingestion points: SKILL.md (Process section, Step 1) instructs the agent to read input from diverse sources including Slack threads, customer complaints, and rough ideas.
  • Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions embedded within the provided input.
  • Capability inventory: The agent has the capability to write formatted text to local markdown files in the thoughts/research/ directory (SKILL.md, Step 5), which are intended to be processed by subsequent tools like backlog-grooming (SKILL.md, Handoffs section).
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the input text before it is processed or saved to the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 01:32 AM