scope-appropriate-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the user's project files (e.g., README, package.json, and source files) to determine project tiers and architectural constraints. Maliciously crafted content in these files could potentially influence the agent's reasoning or behavior.
- Ingestion points: Local project files accessed via the
Read,Glob, andGreptools. - Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent when processing the content of read files.
- Capability inventory: The skill has the ability to execute shell commands for metric collection, perform network operations via
WebFetchandWebSearch, and provide architectural recommendations. - Sanitization: There are no explicit sanitization or validation steps for the content ingested from the codebase.
- [COMMAND_EXECUTION]: The skill uses local shell commands (
find,wc,grep,ls,cat) and an inline Python script to gather codebase metrics such as line counts, file counts, and dependency counts. These commands are used for legitimate project discovery and tier detection.
Audit Metadata