The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external metadata such as ticket IDs, story titles, and developer notes by interpolating them into a markdown report template.
Ingestion points: The skill reads {{story title}}, {{ticket_id}}, and 'Developer Notes' from the current coding manifest as defined in SKILL.md.
Boundary markers: While the report is structured with markdown tables and headers, there are no specific instructions to sanitize or escape these interpolated strings to prevent them from being interpreted as instructions.
Capability inventory: The skill is configured to perform file system writes to the .SS_WF/Agent/CODE/ directory.
Sanitization: No explicit sanitization or input validation logic is described in the provided instructions.
[COMMAND_EXECUTION]: The skill instructions in SKILL.md explicitly forbid the use of shell commands like cat, cp, or sed for document assembly, requiring the agent to use standard file-writing tools instead.
[EXTERNAL_DOWNLOADS]: The skill does not include any network operations, external downloads, or remote script execution patterns.

code-generation-reporting