The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill files.
[PROMPT_INJECTION]: The instructions in SKILL.md are focused on grounding the agent in official documentation and do not contain any patterns designed to bypass safety filters or override system instructions.
[DATA_EXFILTRATION]: There are no hardcoded credentials or instructions to access sensitive local files. Network operations are limited to referencing official AWS documentation links (docs.aws.amazon.com), which are well-known trusted services.
[OBFUSCATION]: No obfuscated content, homoglyphs, zero-width characters, or encoded strings were found in any of the skill files.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute any remote scripts or code. It is purely documentation-based.
[INDIRECT_PROMPT_INJECTION]: While the skill involves reading external data (AWS documentation), this is a surface-level risk that is mitigated by the trusted nature of the target domain (aws.amazon.com). The skill does not provide mechanisms for the ingested data to influence the agent beyond providing factual information.

aws-ecs-docs