configuration-env
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [COMMAND_EXECUTION]: The utility script
scripts/check-config.shaccepts a--startargument which is executed usingbash -lc. This grants the agent the capability to run arbitrary shell commands on the host environment to validate service startup. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze potentially untrusted data from configuration files such as
.env,.env.example, andwrangler.toml. These files could contain hidden instructions that influence the agent's behavior. - Ingestion points: The agent is instructed in
SKILL.mdto read and compare various configuration files including.envandwrangler.*formats. - Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided when the agent processes these configuration files.
- Capability inventory: The skill provides access to shell execution (
bash -lc) and network requests (curl) through thescripts/check-config.shscript. - Sanitization: There is no evidence of sanitization or content validation performed on the ingested files before they are used to generate commands or inform agent actions.
- [DATA_EXFILTRATION]: The skill explicitly targets sensitive files such as
.envandwranglerconfig files which often contain credentials. The scriptscripts/check-config.shincludes network functionality viacurl, which could be used as a channel for data exfiltration if the agent is compromised.
Audit Metadata