The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection attacks because it is designed to ingest and interpret external data that could contain malicious instructions.
Ingestion points: As described in SKILL.md, the skill scans API codebases, AWS infrastructure configuration files, and project documentation.
Boundary markers: The instructions do not specify any delimiters or safety markers to differentiate between the agent's instructions and the untrusted content being scanned.
Capability inventory: The skill is configured with access to Bash(security:*), Bash(scan:*), Bash(audit:*), Write, and Edit tools, which could be abused if an injection is successful.
Sanitization: There are no explicit sanitization or validation steps defined for the content extracted from the target files.
[NO_CODE]: The implementation code for the skill is not included in the provided file set.
The scripts/README.md file lists hipaa_scan.py, config_validator.py, and report_generator.py as the scripts responsible for the skill's logic, but these files are missing.
The assets/README.md file references a report_template.docx that is also not present.

checking-hipaa-compliance