gap-analysis-worksheet

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external requirements documents which could contain hidden instructions designed to influence the agent's analysis or output. * Ingestion points: The skill reads an input document from a user-specified path (Step 1 in SKILL.md). * Boundary markers: Absent. The instructions do not specify the use of delimiters or guidelines to ignore embedded instructions when the agent processes the input content. * Capability inventory: The agent can execute mkdir -p (shell command) and write files to the local filesystem. * Sanitization: Absent. The skill does not describe filtering or escaping the content from the source document before it is analyzed or summarized.
  • [COMMAND_EXECUTION]: The skill executes shell commands to ensure the output directory exists. * Evidence: mkdir -p {base_directory}/requirements in SKILL.md (Step 3). While standard for file management, it represents a direct command execution capability.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 04:00 PM
Security Audit — agent-trust-hub — gap-analysis-worksheet