skills/ascend-ai-coding/awesome-ascend-skills/external-cannbot-ops-pypto-golden-generate/Gen Agent Trust Hub
external-cannbot-ops-pypto-golden-generate
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill generates a Python script (
{op}_golden.py) by populating a template (templates/golden-template.py) with logic derived from operator specifications. This generated script is then automatically executed by the agent to perform validation tests. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of operator specifications, formulas, and input/output descriptions to generate executable code. A maliciously crafted specification could potentially influence the LLM to include unintended or harmful commands in the generated script.
- Ingestion points: Operator specifications, mathematical formulas, and input/output configurations provided by the user in natural language or structured formats (described in §2 and §3 of
SKILL.md). - Boundary markers: The skill does not define explicit boundary markers or instructions to ignore embedded commands within the ingested specification data.
- Capability inventory: The skill has the capability to write files to the local directory and execute them using the
python3interpreter as defined in the validation section (§6). - Sanitization: No explicit sanitization or validation of the generated code logic is mentioned beyond checking for numerical stability and shape consistency.
- [COMMAND_EXECUTION]: The validation process (Section 6) involves the direct execution of shell commands, specifically
python3 {op}_golden.py, to run the generated verification suite.
Audit Metadata