solid-astro
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local files in the
src/directory usinggrepand directory exploration. This creates a surface where malicious instructions embedded in project code could influence agent behavior.\n - Ingestion points: Reads files and executes
grepwithin thesrc/directory.\n - Boundary markers: No specific delimiters or "ignore" instructions are provided for analyzed code content.\n
- Capability inventory: Spawns sub-agents (
fuse-ai-pilot), executes shell commands (grep,find,npx), and accesses file system contents.\n - Sanitization: No input sanitization or validation of analyzed source code is described.\n- [COMMAND_EXECUTION]: The skill uses shell utilities for project analysis.\n
- Evidence: Instructs the use of
grep,find,wc, andawkto enforce file size limits and detect code duplication.\n - Context: Leverages
npx jscpdto check for logic repetition across the codebase.
Audit Metadata