foundation-okr-writer
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists solely of Markdown instructions and reference templates. It does not include any scripts, binary executables, or configurations that interact with the host system or network.
- [NO_CODE]: Comprehensive review of SKILL.md and referenced files (EXAMPLE.md, TEMPLATE.md) confirms the absence of any code execution environment or tool definitions.
- [PROMPT_INJECTION]: No malicious prompt injection or override patterns were detected. The instructions include specific constraints (e.g., refusing to fabricate data or use OKRs for compensation) that serve as safety and quality guardrails for the model's behavior.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any network requests or downloads. Mention of external repositories in the comments is for attribution purposes and does not trigger any automated fetches.
- [DATA_EXPOSURE]: There are no hardcoded credentials, sensitive file paths, or private data access patterns within the skill files.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes untrusted user input (e.g., roadmap items or existing OKR drafts), it lacks any capabilities (such as shell access, file writes, or network tools) that could be exploited via injection.
- Ingestion points: User-provided context and OKR drafts passed to the agent during interaction.
- Boundary markers: Absent; the skill does not define specific delimiters for user-provided data.
- Capability inventory: None; the skill is restricted to text generation.
- Sanitization: Absent; standard LLM safety filters apply.
Audit Metadata