runs-without-me
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to initialize documentation and verify the existence of an overlay directory. Specifically, it uses
mkdirandcpto set up handover files andlsto check for configuration in$POWERSUIT_OVERLAY. These operations are limited to the agent's filesystem scope.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from local files, includingdocs/handover.mdand files within a user-defined overlay directory. If these files are compromised or contain malicious instructions, they could influence the agent's behavior, particularly as the skill instructions state that the overlay should be followed where it disagrees with the default instructions. - Ingestion points:
docs/handover.mdand files within$POWERSUIT_OVERLAY/handover/. - Boundary markers: Absent. There are no explicit delimiters or warnings to treat ingested file content as untrusted.
- Capability inventory: File system access (read/write), directory management, and tool-based ticket creation (
/sdlc:ticket). - Sanitization: Absent. The skill does not specify validation or escaping for the content read from these files.
Audit Metadata