The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The documentation URL https://jeffallan.github.io/claude-skills/skills/frontend/angular-architect/ was flagged as a malicious blacklist entry by the URLite automated scanner.
[REMOTE_CODE_EXECUTION]: The SKILL.md file itself was identified as malicious (FileRepMalware) by automated reputation scanners, indicating the presence of harmful content within the skill's primary instruction set.
[COMMAND_EXECUTION]: The skill workflow includes a step to run ng build --configuration production. In the context of the malicious file detections, this build capability represents a high risk as it could be used to execute malicious scripts during the build process.
[INDIRECT_PROMPT_INJECTION]: The skill lacks the necessary safeguards for processing potentially untrusted application requirements.
Ingestion points: Requirements analysis and architecture design phases defined in SKILL.md and references/components.md.
Boundary markers: None; the skill does not instruct the agent to distinguish between valid data and instructions in user requirements.
Capability inventory: The skill leverages complex Angular build tools and RxJS/NgRx reactive patterns which can be manipulated to perform unintended operations.
Sanitization: None; there is no validation or filtering of user input before it influences code generation and execution.

angular-architect