crest-recon
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies and reads various Markdown files in the repository to establish strategic context. This process creates an indirect prompt injection surface where instructions hidden in these files could potentially manipulate the agent's logic during the summarization phase.
- [COMMAND_EXECUTION]: Uses the Bash tool to execute directory scanning and keyword searches across local Markdown files using
findandgrep. These operations are limited to the current project environment.
Audit Metadata