The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent is instructed to ingest and analyze untrusted third-party source code, configuration files, and binaries. This creates a surface where malicious instructions hidden within the analyzed data (e.g., in comments or metadata) could attempt to influence the agent's behavior during the audit process.
Ingestion points: The "Operational Workflow" in SKILL.md specifies the use of tools for static code/binary inspection, AST analysis, and decompilation on external targets.
Boundary markers: The skill does not provide explicit boundary markers or instructions to the agent to ignore directives embedded within the data it is auditing.
Capability inventory: The instructions involve reading file content, performing discovery on trust boundaries, and implementing remediation code based on the findings.
Sanitization: There is no mention of sanitization or validation of the ingested external content before it is processed by the agent.
[NO_CODE]: The skill consists exclusively of Markdown documentation and YAML metadata files. It does not ship with any executable code, scripts, or binary assets.

offensive-supply-chain