backlog-as-code

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and manipulate an external markdown file (docs/BACKLOG.md). This creates a potential attack surface where instructions hidden within the backlog data could be processed as commands by the agent.
  • Ingestion points: Content is read from docs/BACKLOG.md via the /backlog-list and /backlog-update sub-flows.
  • Boundary markers: The skill does not define any delimiters or provide instructions for the agent to ignore embedded commands within the ingested file content.
  • Capability inventory: The skill possesses the capability to write and modify files on the local filesystem (docs/BACKLOG.md).
  • Sanitization: The provided instructions do not include any logic for validating, escaping, or filtering the data retrieved from the backlog file before it is used in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 08:14 PM
Security Audit — agent-trust-hub — backlog-as-code