The Agent Skills Directory

[SAFE]: The skill is a procedural framework for software debugging, emphasizing reproduction, ranking hypotheses, and targeted fixes. It aligns with standard development best practices and does not include any executable scripts, remote downloads, or credential-harvesting patterns.
[INDIRECT_PROMPT_INJECTION]: As a debugging tool, the skill is designed to ingest and analyze potentially untrusted data such as error logs, stack traces, and bug reproduction steps. This represents a standard surface for indirect prompt injection, though it is inherent to the primary function of debugging.
Ingestion points: The agent is instructed to process user-provided bug reports, external stack traces, and reproduction inputs as described in the Phase 1 (Reproduce) section of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or guards for segregating external log data from the agent's control instructions.
Capability inventory: The skill allows for the use of version control tools (git log, git diff), shell execution for reproducing bugs, and code generation for applying fixes (SKILL.md).
Sanitization: The skill relies on the agent's internal analysis and manual instrumentation rather than automated sanitization of log content.

systematic-debugging