The Agent Skills Directory

[SAFE]: The skill is a maintenance utility that manages internal project documentation and git metadata. It operates within the 'fork' context and does not exhibit any patterns of data exfiltration, credential theft, or unauthorized persistence.
[COMMAND_EXECUTION]: The skill relies on shell commands (e.g., git log, find, mkdir) and vendor-specific CLI tools (ao, bd) to perform repository analysis and file management. These operations are consistent with the skill's stated purpose of knowledge intelligence and are used in a non-destructive manner.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests untrusted data from git logs and external research files which could theoretically contain malicious instructions targeting the agent's reasoning phase.
Ingestion points: Extracts signal from git history (git log), .agents/research/*.md, and .agents/learnings/*.md.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the data files being processed.
Capability inventory: The skill has the capability to execute shell commands (git, ao, bd) and perform file-system writes in the .agents/ directory.
Sanitization: No explicit sanitization or content filtering is described for the data ingested during the Mine and Grow phases.

athena