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 viewas described inSKILL.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, includinggh issue view,gh issue close, andgh issue commentbased on user interactions and project state.
Audit Metadata