formula-derivation
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection as it ingests untrusted external data which could contain hidden instructions for the agent.
- Ingestion points: The skill reads local context from user-specified files, derivation drafts, and theory notes in 'Step 1: Gather Derivation Context'.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the processed data files.
- Capability inventory: The skill uses tools for file system interaction including 'Read', 'Write', 'Edit', 'Grep', and 'Glob', providing a mechanism for the agent to modify the project environment based on instructions.
- Sanitization: No sanitization, validation, or filtering of the ingested note content is specified before the agent processes the information.
Audit Metadata