project-core-dev
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions guide the agent to ingest data from repository files such as README, CI configuration, and contributor docs. This creates an attack surface where instructions embedded in these untrusted files could influence agent behavior.
- Ingestion points: SKILL.md explicitly directs the agent to read repository instructions, README, CI configuration, contributor docs, and presets.
- Boundary markers: The skill lacks instructions for using delimiters or warnings to ignore potentially malicious embedded instructions in the external content.
- Capability inventory: The skill permits the agent to execute authoritative commands identified within the repository's internal documentation.
- Sanitization: There are no mentions of sanitization, filtering, or validation steps for content sourced from the repository files.
Audit Metadata