The Agent Skills Directory

[PROMPT_INJECTION]: The skill's primary function is to read and analyze project files (such as package.json, README.md, and application source code) to perform security assessments. This functionality creates an attack surface for indirect prompt injection, where instructions hidden within the audited codebase could attempt to manipulate the agent's findings or behavior.\n
Ingestion points: The agent is instructed to read local codebase files, including reconnaissance targets like README.md, CLAUDE.md, and dependency manifests.\n
Boundary markers: There are no explicit delimiters or instructions defined to help the agent distinguish between its system instructions and the data it is auditing.\n
Capability inventory: The skill performs file system read operations to analyze the project and file system write operations to save reports in the audit-reports/ and planning-docs/ directories.\n
Sanitization: The skill does not describe any sanitization or validation of the ingested data before it is processed or included in generated reports.

nehemiah-security