fstack-learn

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill reads and appends content to the LEARNED.md file in the project root. This file system access is required for its primary function and is restricted to markdown files.
  • [INDIRECT_PROMPT_INJECTION]: 1. Ingestion points: The skill processes 'recent work' and the existing LEARNED.md file to identify lessons (SKILL.md). 2. Boundary markers: No delimiters or instructions to ignore embedded commands are present when analyzing the input data. 3. Capability inventory: The skill has file-write capabilities through its ability to create or append to the LEARNED.md file (SKILL.md). 4. Sanitization: There is no validation or escaping of the ingested content before it is formatted into an entry and appended to the log file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 08:59 AM
Security Audit — agent-trust-hub — fstack-learn