summon
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No evidence of instructions attempting to bypass safety filters or override agent behavior was found. The skill includes explicit instructions to refuse deceptive uses and maintain role boundaries.
- [DATA_EXFILTRATION]: The skill does not perform network operations to untrusted domains or access sensitive system files like credentials or SSH keys.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of remote scripts, nor does the skill use dynamic execution functions like eval or exec.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or private secrets were detected in the source code or reference files. Guidance for managing profiles suggests local workspace storage only.
- [OBFUSCATION]: The skill uses clear, human-readable markdown and YAML with no hidden characters, Base64-encoded instructions, or homoglyph substitutions.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes external information for figure research, it mitigates injection risks by requiring all claims to be tagged with attestation tiers (ATTESTED, INFERRED, SPECULATIVE) and running a mandatory 'Ethics Gate' that refuses deceptive or undocumented uses.
Audit Metadata