tsg-flow-capability-backlog

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources to generate a business backlog, creating a surface for indirect instructions to influence the agent.
  • Ingestion points: The skill reads content from vision.md, context/domain-map.md, and context/architecture-baseline.md (SKILL.md).
  • Boundary markers: There are no specified delimiters or instructions for the agent to ignore or isolate potentially malicious instructions embedded within these source files.
  • Capability inventory: The skill possesses the capability to write to the file system, specifically creating backlog/capabilities.md and updating flow-state.json (SKILL.md).
  • Sanitization: The instructions do not define any filtering, validation, or escaping mechanisms for the data ingested from the source files before it is used to generate the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:41 PM