The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill generates and executes Python code snippets by piping them into the Django management shell (python manage.py shell) using shell here-docs (EOF).
Evidence: Found in Phase 6 (superuser creation), Phase 7 (database index verification), Phase 9 (configuration review), and Phase 10 (logging tests) within SKILL.md.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could be influenced by an attacker, creating a surface for indirect prompt injection.
Ingestion points: The skill reads output from git diff and parses security reports such as bandit-report.json in SKILL.md.
Boundary markers: No delimiters or specific warnings are used to differentiate untrusted code/logs from instructions.
Capability inventory: The skill has extensive shell execution capabilities, including database access and package management tools.
Sanitization: No sanitization or validation of the ingested data is performed before it enters the agent's context.
[COMMAND_EXECUTION]: The skill executes a wide array of system commands and development utilities including pip, npm, git, and python manage.py to perform its verification tasks.

django-verification