interview-loop

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands to verify directory existence and manage local template files.
  • Evidence: mkdir -p hiring && cp -n "${CLAUDE_PLUGIN_ROOT}/templates/hiring/loop.md" hiring/loop.md used for template initialization.
  • Evidence: [ -n "$POWERSUIT_OVERLAY" ] && ls -1 "$POWERSUIT_OVERLAY/hiring" 2>/dev/null || true used to check for local configuration overlays.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon instructions from an external "overlay" directory if the $POWERSUIT_OVERLAY environment variable is set.
  • Ingestion points: README.md and other files within the $POWERSUIT_OVERLAY/hiring/ path are ingested to modify agent behavior.
  • Boundary markers: Absent; the instructions dictate that the overlay content should be prioritized over the skill's default behavior, which is the intended configuration mechanism.
  • Capability inventory: File system management (mkdir, cp, ls) and markdown-based documentation generation.
  • Sanitization: No specific sanitization or validation of the overlay file content is performed, as it is treated as an authoritative configuration source for the specific project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 12:50 PM