pseo-performance
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes shell commands for bundle analysis (
ANALYZE=true next build) and memory tracking (/usr/bin/time -v next build). These are standard diagnostic tools used in web development and do not demonstrate malicious intent. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data for programmatic page generation, which introduces an attack surface for indirect prompt injection.
- Ingestion points: Data is sourced from external providers via functions such as
fetchAllIndexDataFromSourceandfetchSinglePage(slug)inSKILL.md. - Boundary markers: The provided implementation patterns lack specific delimiters or instructions to isolate the agent from potentially malicious commands embedded in the source content.
- Capability inventory: The skill is granted access to powerful tools (
Bash,Write,Edit,Glob), which could be misused if the agent inadvertently follows instructions found in the ingested data. - Sanitization: There are no guidelines or code snippets provided for sanitizing or validating the ingested content before it is processed by the agent.
Audit Metadata