paper-ds-tokens
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes and synchronizes data from external sources, including Figma, source code, and local configuration files, which presents a surface for indirect prompt injection if these sources are compromised.
- Ingestion points: The skill reads token snapshots and manifests from relative file paths such as
../paper-ds-manage/references/versioning.mdand../paper-ds-options/references/comparisons.md, as well as from external tools (Figma and code repositories). - Boundary markers: There are no explicit markers or instructions provided to delimit untrusted data from the agent's core instructions.
- Capability inventory: The skill is authorized to use
create_tokensandset_tokensand can perform write operations back to source code repositories during 'pull' or 'generate' workflows. - Sanitization: No specific sanitization, validation, or escaping mechanisms for external content are defined in the skill logic.
Audit Metadata