competition-submission-checker
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and act upon data from untrusted or external project files which may contain embedded instructions.
- Ingestion points: The agent is directed to read instructions and context from
AGENTS.md,docs/memory-bank/progress.md, and projectREADMEfiles. - Boundary markers: There are no instructions to treat content from these external files as untrusted or to ignore instructions embedded within them.
- Capability inventory: The skill does not provide its own scripts or commands, relying instead on the agent's inherent file-reading capabilities.
- Sanitization: No sanitization or validation logic is defined for the content read from external documentation.
- [NO_CODE]: The skill contains only documentation and instruction files (SKILL.md and CHANGELOG.md). No scripts, executables, or dynamic execution patterns were detected.
Audit Metadata