The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions found that attempt to override system prompts, bypass safety filters, or extract underlying configurations.
[Data Exposure & Exfiltration] (SAFE): The skill does not access sensitive local files or perform any network operations to external domains.
[Unverifiable Dependencies & Remote Code Execution] (SAFE): There are no package installations (npm/pip) or scripts that download and execute code from remote sources.
[Dynamic Execution] (SAFE): No use of eval(), exec(), or runtime compilation techniques detected. The skill uses 'disable-model-invocation: true', further limiting its capability to execute actions.
[Persistence & Privilege Escalation] (SAFE): No attempts to modify shell profiles, system services, or acquire elevated permissions (sudo).
[Indirect Prompt Injection] (SAFE): While the skill processes user inputs to generate roadmaps, it lacks any high-privilege capabilities (like network or file system access) that could be exploited by malicious data.

pm-roadmap