aps-doc-golden
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, obfuscation, persistence mechanisms, or unauthorized privilege escalation were detected. The skill's behavior is consistent with its stated purpose of documentation generation.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses local codebase files including SQL queries and workflow configurations. This access is necessary for extracting technical metadata and is restricted to the directory path explicitly provided by the user. No evidence of credential harvesting, hardcoded secrets, or network exfiltration was found.
- [COMMAND_EXECUTION]: The skill utilizes file system discovery (globbing) to identify relevant files for analysis. This is a standard and safe operation for documentation tools and does not involve the execution of arbitrary shell commands or external binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files (SQL and YAML). While processing external content always presents an inherent surface for indirect prompt injection, the risk is minimal as the skill is focused on structured extraction and summarization of code logic without executable side effects.
Audit Metadata