open-knowledge-pack-software-lifecycle-write-a-spec

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill implements a documentation workflow for software lifecycle management, focusing on scoping features and writing implementation specs.
  • [COMMAND_EXECUTION]: The skill utilizes exec, write, edit, and search functions. Based on the compatibility metadata, these are tool calls provided by the OpenKnowledge MCP server. The usage is restricted to local file operations such as listing directories (ls -A), reading documents (cat), and searching the repository contents.
  • [DATA_EXFILTRATION]: The skill instructions involve reading local source code (.ts, .py, schemas) and project documentation. However, there are no network operations or instructions to transmit this information to external or untrusted domains. All data remains within the local project environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository, including user-written proposals and source code comments. While it does not specify explicit sanitization logic for these inputs, the risk is low as the output is structured markdown documentation and the workflow requires following a strict mandatory execution order with human-supervised gates by default.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:16 AM
Security Audit — agent-trust-hub — open-knowledge-pack-software-lifecycle-write-a-spec