explain-step-by-step
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown text and YAML metadata. It does not include any scripts (Python, JavaScript, shell), binaries, or configuration files that could execute commands.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to process untrusted external data sources such as code, PRs, and technical documents.
- Ingestion points: The 'Ground the Explanation' section of
SKILL.mdinstructs the agent to inspect available sources (code, errors, PRs, issues, documents) before explaining. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the source material.
- Capability inventory: The skill has no capabilities; it performs no file writes, network operations, or shell executions.
- Sanitization: No sanitization or filtering logic is present for the ingested data.
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of providing structured explanations.
Audit Metadata