Secret safety for AWS Secrets Manager, secret management, credentials, API keys, tokens, and passwords. Prevents AI agents from directly fetching secret values and teaches runtime dynamic references with asm-exec so plaintext never enters the LLM context window.
70%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./plugins/aws-core/skills/aws-secrets-manager/SKILL.mdDetected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill's purpose is protecting secrets, and its code and endpoints are consistent with that; the only sketchy content is a documented example that writes a resolved plaintext password to a world-readable /tmp file, which is careless rather than malicious.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow resolves the user's own Secrets Manager entries through SMA or the AWS MCP endpoint, which is first-party tenant data, but the examples also have the agent run user-chosen commands (e.g., `psql ... SELECT * FROM users`, `curl .../data`) whose output returns to context, so outsider-authored text could reach the agent only when the agent actively fetches or queries a user-specified service.
aws/agent-toolkit-for-aws
292edb1
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.