superpowers-issue-bridge

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external issue trackers (e.g., GitHub issue titles and bodies) and treats this content as established constraints or answers for the AI's brainstorming process.
  • Ingestion points: Data is fetched via tracker-specific methods, such as gh issue view as described in SKILL.md.
  • Boundary markers: There are no instructions to use delimiters or specific boundary markers to isolate the external issue content from the agent's primary instructions.
  • Capability inventory: The skill has the ability to write specification and plan files to the local file system (e.g., docs/superpowers/specs/) and execute shell commands via the GitHub CLI.
  • Sanitization: There is no evidence of sanitization, escaping, or validation of the external issue content before it is interpolated into the agent's context.
  • [COMMAND_EXECUTION]: The instructions direct the agent to execute shell commands using the GitHub CLI (gh) to interact with issues, including gh issue view, gh issue close, and gh issue comment based on user interactions and project state.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 01:49 PM
Security Audit — agent-trust-hub — superpowers-issue-bridge