The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override agent behavior were found. The language used is purely instructional and consistent with the stated purpose.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration commands (like curl or wget) are present.
[Remote Code Execution] (SAFE): The skill does not download or execute remote scripts, nor does it define any unverifiable dependencies.
[Indirect Prompt Injection] (LOW): The skill's primary function is to help an agent process business requirements and user stories, which are untrusted external inputs. This represents a potential attack surface.
Ingestion points: Requirements, stories, and rules provided via the Read tool.
Boundary markers: None specified in the skill text.
Capability inventory: The skill allows use of Bash and Read tools, though no specific implementation code is provided.
Sanitization: No sanitization methods are defined within the skill.

bdd-collaboration